MEDIA ANALYTICS
PROJECTS
PEOPLE
PATENTS
This paper proposes AutoScape, a long-horizon driving scene generation framework. At its core is a novel RGB-D diffusion model that iteratively generates sparse, geometrically consistent keyframes, serving as reliable anchors for the scenes appearance and geometry. To maintain long-range geometric consistency,
Visual reasoning (VR), which is crucial in many fields for enabling human-like visual understanding, remains highly challenging. Recently, compositional visual reasoning approaches, which leverage the reasoning abilities of large language models (LLMs) with integrated tools to solve problems, have shown
Evaluating autonomous vehicles with controllability enables scalable testing in counterfactual or structured settings, enhancing both efficiency and safety. We introduce LangTraj, a language-conditioned scene-diffusion model that simulates the joint behavior of all agents in traffic scenarios. By conditioning
Obtaining high-quality fine-grained annotations for traffic signs is critical for accurate and safe decision-making in autonomous driving. Widely used datasets, such as Mapillary, often provide only coarse-grained labels without distinguishing semantically important types such as stop signs or speed
Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of structured inductive biases. As vision is often the sole modality available for such analysis (i.e., no LiDAR, GPS, etc.), existing
A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. With efficiency being a high priority for scaling such models, we observed that the state-of-the-art method Mask2Former uses >50% of its compute
Spatio-temporal reasoning is essential in understanding real-world environments in various fields, eg, autonomous driving and sports analytics. Recent advances have improved the spatial reasoning ability of Vision-Language Models (VLMs) by introducing large-scale data, but these models still struggle
The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the synthetic nature of such 3D data, their performance drops significantly when applied to real-world images. This paper consolidates
Evaluating the performance of autonomous vehicle planning algorithms necessitates simulating long-tail safety-critical traffic scenarios. However, traditional methods for generating such scenarios often fall short in terms of controllability and realism; they also neglect the dynamics of agent interactions.
Lensless cameras multiplex the incoming light before it is recorded by the sensor. This ability to multiplex the incoming light has led to the development of ultra-thin, high-speed, and single-shot 3D imagers. Recently, there have been various attempts at demonstrating another useful aspect of lensless
We propose a vision-LLM framework for automating development and deployment of computer vision solutions for pre-defined or custom-defined tasks. A foundational layer is proposed with a code-LLM AI orchestrator self-trained with reinforcement learning to create Python code based on its understanding
Recent studies have shown promising performance in open-vocabulary object detection (OVD) by utilizing pseudo labels (PLs) from pretrained vision and language models (VLMs). However, teacher-student self-training, a powerful and widely used paradigm to leverage PLs, is rarely explored for OVD.
Autonomous vehicle (AV) systems rely on robust perception models as a cornerstone of safety assurance. However, objects encountered on the road exhibit a long-tailed distribution, with rare or unseen categories posing challenges to a deployed perception model. This necessitates an expensive process of
Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot prompting with frozen LLMs to synthesize visual programs. Training an LLM to write better visual programs is an attractive
The perception of 3D motion of surrounding traffic participants is crucial for driving safety. While existing works primarily focus on general large motions, we contend that the instantaneous detection and quantification of subtle motions is equally important as they indicate the nuances in driving behavior
Photorealistic simulation plays a crucial role in applications such as autonomous driving, where advances in neural radiance fields (NeRFs) may allow better scalability through the automatic creation of digital 3D assets. However, reconstruction quality suffers on street scenes due to largely collinear
This report aims to provide a comprehensive view on the inference efficiency of DETR-style detection models. We provide the effect of the basic efficiency techniques and identify the factors that are easily applicable yet effectively improve the efficiency-accuracy trade-off. Specifically, we explore
The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective function has proven successful, but requires good positive and negative
We aim to address key challenges in long-horizon embodied exploration and navigation by proposing a long-horizon object transport task called Long-HOT and a novel modular framework for temporally extended navigation. Agents in Long-HOT need to efficiently find and pick up target objects that are scattered
Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be taxing on deployed devices. One way to overcome this challenge
The recent progress in language-based object detection with an open-vocabulary can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training from image captions with grounded bounding boxes (ground truth or pseudo-labeled) enable the models
Visual question answering (VQA) has traditionally been treated as a single-step task where each question receives the same amount of effort, unlike natural human question-answering strategies. We explore a question decomposition strategy for VQA to overcome this limitation. We probe the ability of recently
Data augmentation techniques, such as image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are fundamentally incompatible with differentially private learning approaches,
Evaluating the performance of autonomous vehicle planning algorithms necessitates simulating long-tail traffic scenarios. Traditional methods for generating safety-critical scenarios often fall short in realism and controllability. Furthermore, these techniques generally neglect the dynamics of agent
Although planning is a crucial component of the autonomous driving stack, researchers have yet to develop robust planning algorithms that are capable of safely handling the diverse range of possible driving scenarios. Learning-based planners suffer from overfitting and poor long-tail performance. On
Lensless cameras multiplex the incoming light before it is recorded by the sensor. This ability to multiplex the incoming light has led to the development of ultra-thin, high-speed, and single-shot 3D imagers. Recently, there have been various attempts at demonstrating another useful aspect of lensless
Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. To compensate for the over-parameterized models, numerous regularization techniques have been introduced such as those based on dropout. While these methods achieve significant improvements on classical
We aim to train a multi-task model such that users can adjust the desired compute budget and relative importance of task performances after deployment, without retraining. This enables optimizing performance for dynamically varying user needs, without heavy computational overhead to train and save models
Modern computer vision services often require users to share raw feature descriptors with an untrusted server. This presents an inherent privacy risk, as raw descriptors may be used to recover the source images from which they were extracted. To address this issue, researchers recently proposed privatizing
Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent methods show great progress in that direction, proper evaluation is lacking. With OmniLabel, we propose a novel task definition,
Recent studies show promising performance in open-vocabulary object detection (OVD) using pseudo labels (PLs) from pretrained vision and language models (VLMs). However, PLs generated by VLMs are extremely noisy due to the gap between the pretraining objective of VLMs and OVD, which blocks further advances
Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy Estimation This work aims to assess how well a model performs under distribution shifts without using labels. While recent methods study prediction confidence, this work reports prediction dispersity is another
Monocular 3D object localization in driving scenes is a crucial task, but challenging due to its ill-posed nature. Estimating 3D coordinates for each pixel on the object surface holds great potential as it provides dense 2D-3D geometric constraints for the underlying PnP problem. However, high-quality
Finetuning a large vision language model (VLM) on a target dataset after large scale pretraining is a dominant paradigm in visual question answering (VQA). Datasets for specialized tasks such as knowledge-based VQA or VQA in non natural-image domains are orders of magnitude smaller than those for general-purpose
This paper presents an approach to train a unified deep network that simultaneously solves multiple human-related tasks. A multi-task framework is favorable for sharing information across tasks under restricted computational resources. However, tasks not only share information but may also compete for
Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We propose a novel method that leverages the rich semantics available
With over a billion sold each year, cameras are not only becoming ubiquitous, but are driving progress in a wide range of domains such as mixed reality, robotics, and more. However, severe concerns regarding the privacy implications of camera-based solutions currently limit the range of environments
While it is desirable to train segmentation models on an aggregation of multiple datasets, a major challenge is that the label space of each dataset may be in conflict with one another. To tackle this challenge, we propose UniSeg, an effective and model-agnostic approach to automatically train segmentation
Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global level. Earlier, supervised, non-contrastive methods were capable
Multi-task learning commonly encounters competition for resources among tasks, specifically when model capacity is limited. This challenge motivates models which allow control over the relative importance of tasks and total compute cost during inference time. In this work, we propose such a controllable
Convolutional Neural Networks have achieved remarkable success in face recognition, in part due to the abundant availability of data. However, the data used for training CNNs is often imbalanced. Prior works largely focus on the long-tailed nature of face datasets in data volume per identity or focus
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for 3D semantic segmentation. We find that, directly applying existing
Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks of-ten suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recent methods focus on preventing catastrophic forgetting under the assumption of train
We propose an end-to-end network that takes a single perspective RGB image of a complex road scene as input, to produce occlusion-reasoned layouts in perspective space as well as a parametric bird’s-eye-view (BEV) space. In contrast to prior works that require dense supervision such as semantic labels
This work aims to assess how well a model performs under distribution shifts without using labels. While recent methods study prediction confidence, this work reports prediction dispersity is another informative cue. Confidence reflects whether the individual prediction is certain, dispersity indicates
Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has been derived from the RGB image space. However, video data is
Face recognition models trained under the assumption of identical training and test distributions often suffer from poor generalization when faced with unknown variations, such as a novel ethnicity or unpredictable individual make-ups during test time. In this paper, we introduce a novel cross-domain
Trajectory prediction is a safety-critical tool for autonomous vehicles to plan and execute actions. Our work addresses two key challenges in trajectory prediction, learning multimodal outputs, and better predictions by imposing constraints using driving knowledge. Recent methods have achieved strong
Learning methods for relative camera pose estimation have been developed largely in isolation from classical geometric approaches. The question of how to integrate predictions from deep neural networks (DNNs) and solutions from geometric solvers, such as the 5-point algorithm [37], has as yet remained
In this paper, we focus on exploring the fusion of images and point clouds for 3D object detection in view of the complementary nature of the two modalities, i.e., images possess more semantic information while point clouds specialize in distance sensing. To this end, we present a novel two-stage multi-modal
Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss. The triplet loss used in video re-ID is usually based on so-called clip features, each aggregated from a few frame features. In this paper, we propose to model the
Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks. In this work, we propose a fully attentional network, termed channel recurrent attention network, for the task of video pedestrian retrieval.
Face anti-spoofing (FAS) seeks to discriminate genuine faces from fake ones arising from any type of spoofing attack. Due to the wide variety of attacks, it is implausible to obtain training data that spans all attack types. We propose to leverage physical cues to attain better generalization on unseen
Differentially Private Federated Learning (DPFL) is an emerging field with many applications. Gradient averaging-based DPFL methods require costly communication rounds and hardly work with large capacity models due to the explicit dimension dependence in its added noise. In this work, inspired by knowledge
We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter- and intra-domain variation. While deep domain adaptation methods have been realized by reducing the domain discrepancy, these
Classical monocular Simultaneous Localization And Mapping (SLAM) and the recently emerging convolutional neural networks (CNNs) for monocular depth prediction represent two largely disjoint approaches towards building a 3D map of the surrounding environment. In this paper, we demonstrate that the coupling
We propose a novel framework for domain adaptation in semantic segmentation with image-level weak labels in the target domain. The weak labels may be obtained based on a model prediction for unsupervised domain adaptation (UDA), or from a human oracle in a new weakly-supervised domain adaptation (WDA)
In this paper, we derive a new differential homography that can account for the scanline-varying camera poses in Rolling Shutter (RS) cameras, and demonstrate its application to carry out RS-aware image stitching and rectification at one stroke. Despite the high complexity of RS geometry, we focus in
While deep face recognition has benefited significantly from large-scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation. Prior work has mostly been in controlled settings, where the labeled and unlabeled data
Monocular visual odometry (VO) suffers severely from error accumulation during frame-to-frame pose estimation. In this paper, we present a self-supervised learning method for VO with special consideration for consistency over longer sequences. To this end, we model the long-term dependency in pose prediction
We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers that are specific to individual domains. Our approach employs multiple normalization methods while learning separate affine parameters per domain.
Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant—application-relevant categories can be picked and merged form
We address the problem of domain adaptation in videos for the task of human action recognition. Inspired by image-based domain adaptation, we can perform video adaptation by aligning the features of frames or clips of source and target videos. However, equally aligning all clips is sub-optimal as not
We propose advances that address two key challenges in future trajectory prediction: (i) multimodality in both training data and predictions and (ii) constant time inference regardless of number of agents. Existing trajectory predictions are fundamentally limited by lack of diversity in training data,
Read Improving Face Recognition by Clustering Unlabeled Faces in the Wild (arXiv). While deep face recognition has benefited significantly from large scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation. Prior
We address the challenging task of occlusion-aware indoor 3D scene understanding. We represent scenes by a set of planes, where each one is defined by its normal, offset and two masks outlining (i) the extent of the visible part and (ii) the full region that consists of both visible and occluded parts
With increasing ethical and legal concerns on privacy for deep models in visual recognition, differential privacy has emerged as a mechanism to disguise membership of sensitive data in training datasets. Recent methods like Private Aggregation of Teacher Ensembles (PATE) leverage a large ensemble of
Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domains, or by introducing unlabeled target variation data to adapt from the training data. Instead, we propose a universal representation
In this paper, we address the problem of inferring the layout of complex road scenes from video sequences. To this end, we formulate it as a top-view road attributes prediction problem and our goal is to predict these attributes for each frame both accurately and consistently. In contrast to prior work,
We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance sampling for adapting models across domains. The former uses
We present an audio-visual multimodal approach for the task of zero-shot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities
Blind video deblurring restores sharp frames from a blurry sequence without any prior. It is a challenging task because the blur due to camera shake, object movement and defocusing is heterogeneous in both temporal and spatial dimensions. Traditional methods train on datasets synthesized with a single
We address the problem of human action classification in drone videos. Due to the high cost of capturing and labeling large-scale drone videos with diverse actions, we present unsupervised and semi-supervised domain adaptation approaches that leverage both the existing fully annotated action recognition
We address the challenging task of video-based person re-identification. Recent works have shown that splitting the video sequences into clips and then aggregating clip-based similarity is appropriate for the task. We show that using a learned clip similarity aggregation function allows filtering out
Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model inversion attack, whose goal is to reconstruct the input data
Self-calibration of camera intrinsics and radial distortion has a long history of research in the computer vision community. However, it remains rare to see real applications of such techniques to modern Simultaneous Localization And Mapping (SLAM) systems, especially in driving scenarios. In this paper,
We address the problem of 3D object detection from 2D monocular images in autonomous driving scenarios. We propose to lift the 2D images to 3D representations using learned neural networks and leverage existing networks working directly on 3D data to perform 3D object detection and localization. We show
Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models trained on one data domain may not generalize well to other domains without annotations for model finetuning. To avoid the
Traditional intrinsic image decomposition focuses on decomposing images into reflectance and shading, leaving surfaces normals and lighting entangled in shading. In this work, we propose a Global-Local Spherical Harmonics (GLoSH) lighting model to improve the lighting component, and jointly predict reflectance
Read Deep Supervision with Intermediate Concepts (IEEE). Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both human
We address the challenging problem of generating facial attributes using a single image in an unconstrained pose. In contrast to prior works that largely consider generation on 2D near-frontal images, we propose a GAN-based framework to generate attributes directly on a dense 3D representation given
We introduce a novel dataset for high-level 3D scene understanding of complex road scenes. Our annotations extend the existing datasets KITTI [5] and nuScenes [1] with semantically and geometrically meaningful attributes like the number of lanes or the existence of, and distance to, intersections, sidewalks
In this paper, we address the problem of inferring the layout of complex road scenes given a single camera as input. To achieve that, we first propose a novel parameterized model of road layouts in a top-view representation, which is not only intuitive for human visualization but also provides an interpretable
Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such significant portion results in insufficient training data. Training with under-represented data leads to biased classifiers
Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels. We propose that advantages may be derived by combining them, in the form of different insights that lead to a
An exact method of correcting the rolling shutter (RS) effect requires recovering the underlying geometry, i.e. the scene structures and the camera motions between scanlines or between views. However, the multiple-view geometry for RS cameras is much more complicated than its global shutter (GS) counterpart,
We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces. In contrast to previous attempts, our model runs without the aid of spectral clustering. This makes our algorithm one of the kinds that can
Unsupervised domain adaptation is a promising avenue to enhance the performance of deep neural networks on a target domain, using labels only from a source domain. However, the two predominant methods, domain discrepancy reduction learning and semi-supervised learning, are not readily applicable when
Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire. In this work, we propose a reinforcement learning-based method for automatically adjusting the parameters of any (non-differentiable) simulator, thereby controlling
Attribute-conditioned face synthesis has many potential use cases, such as to aid the identification of a suspect or a missing person. Building on top of a conditional version of VAE-GAN, we augment the pathways connecting the latent space with channel-recurrent architecture, in order to provide not
We propose a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore motion when aligning features over time, or operate in an off-line mode to utilize future frames.
Subspace clustering algorithms are notorious for their scalability issues because building and processing large affinity matrices are demanding. In this paper, we introduce a method that simultaneously learns an embedding space along subspaces within it to minimize a notion of reconstruction error, thus
In order to learn object segmentation models in videos, conventional methods require a large amount of pixel-wise ground truth annotations. However, collecting such supervised data is time-consuming and labor-intensive. In this paper, we exploit existing annotations in source images and transfer such
We claim that there is currently no satisfactory way to regularize a generative adversarial network (GAN): neither the generator nor discriminator is particularly amenable to the imposition of inductive biases derived from domain knowledge. A generator is effectively a causal model of generationone
Unsupervised domain adaptation is an attractive avenue to enhance the performance of deep neural networks in a target domain, using labels only from a source domain. However, two predominant methods along this line, namely, domain divergence reduction learning and semi-supervised learning, are not readily
Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We demonstrate that commonly used metric learning approaches do
We propose a method to forecast a vehicle’s ego-motion as a distribution over spatiotemporal paths, conditioned on features (e.g., from LIDAR and images) embedded in an overhead map. The method learns a policy inducing a distribution over simulated trajectories that is both diverse (produces most paths
Given a single RGB image of a complex outdoor road scene in the perspective view, we address the novel problem of estimating an occlusion-reasoned semantic scene layout in the top-view. This challenging problem not only requires an accurate understanding of both the 3D geometry and the semantics of the
We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training. We work with a challenging set of object classes, not restricting ourselves to similar and/or fine-grained categories as in prior works on zero-shot classification.
Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for
Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to the
This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning features over time, or operate in an off-line mode to utilize
Real-world face recognition datasets exhibit long-tail characteristics, which results in biased classifiers in conventionally-trained deep neural networks, or insufficient data when long-tail classes are ignored. In this paper, we propose to handle long-tail classes in the training of a face recognition
Despite recent successes in synthesizing faces and bedrooms, existing generative models struggle to capture more complex image types (Figure 1), potentially due to the oversimplification of their latent space constructions. To tackle this issue, building on Variational Autoencoders (VAEs), we integrate
Light-field cameras have recently emerged as a powerful tool for one-shot passive 3D shape capture. However, obtaining the shape of glossy objects like metals or plastics remains challenging, since standard Lambertian cues like photo-consistency cannot be easily applied. In this paper, we derive a spatially-varying
Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels. We propose that advantages may be derived by combining them, in the form of different insights that lead to a
Large-scale training for semantic segmentation is challenging due to the expense of obtaining training data for this task relative to other vision tasks. We propose a novel training approach to address this difficulty. Given cheaply-obtained sparse image labelings, we propagate the sparse labels to produce
We introduce a new light-field dataset of materials and take advantage of the recent success of deep learning to perform material recognition on the 4D light field. Our dataset contains 12 material categories, each with 100 images taken with a Lytro Illum, from which we extract about 30,000 patches in
We present a physically interpretable 3D model for handling occlusions with applications to road scene understanding. Given object detection and SFM point tracks, our unified model probabilistically assigns point tracks to objects and reasons about object detection scores and bounding boxes. It uniformly
Our WarpNet matches images of objects in fine-grained datasets without using part annotations. It aligns an object in one image with a different object in another by exploiting a fine-grained dataset to create artificial data for training a Siamese network with an unsupervised discriminative learning
We propose a novel framework for monocular traffic scene recognition, relying on a decomposition into high-order and atomic scenes to meet those challenges. High-order scenes carry semantic meaning useful for AWS applications, while atomic scenes are easy to learn and represent elemental behaviors based
This paper investigates a novel problem of generating images from visual attributes. We model the image as a composite of foreground and background and develop a layered generative model with disentangled latent variables that can be learned end-to-end using a variational auto-encoder. We experiment
