Bingbing Zhuang NEC Labs America

Bingbing Zhuang

Researcher

Media Analytics

Posts

NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization

/in /by

NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization 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 ground truth supervision is not available in driving scenes due to sparsity and various artifacts of Lidar data, as well as the practical infeasibility of collecting per-instance CAD models. In this work, we present NeurOCS, a framework that uses instance masks and 3D boxes as input to learn 3D object shapes by means of differentiable rendering, which further serves as supervision for learning dense object coordinates. Our approach rests on insights in learning a category-level shape prior directly from real driving scenes, while properly handling single-view ambiguities. Furthermore, we study and make critical design choices to learn object coordinates more effectively from an object-centric view. Altogether, our framework leads to new state-of-the-art in monocular 3D localization that ranks 1st on the KITTI-Object benchmark among published monocular methods.

Read more

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

/in /by

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation 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 methods usually results in performance instability at test time, because multi-modal input is not considered jointly. To design a framework that can take full advantage of multi-modality, where each modality provides regularized self-supervisory signals to other modalities, we propose two complementary modules within and across the modalities. First, Intra-modal Pseudo-label Generation (Intra-PG) is introduced to obtain reliable pseudo labels within each modality by aggregating information from two models that are both pre-trained on source data but updated with target data at different paces. Second, Inter-modal Pseudo-label Refinement (Inter-PR) adaptively selects more reliable pseudo labels from different modalities based on a proposed consistency scheme. Experiments demonstrate that our regularized pseudo labels produce stable self-learning signals in numerous multi-modal test-time adaptation scenarios for 3D semantic segmentation. Visit our project website at https://www.nec-labs.com/~mas/MM-TTA

Read more

Weakly But Deeply Supervised Occlusion-Reasoned Parametric Road Layouts

/in /by

Weakly But Deeply Supervised Occlusion-Reasoned Parametric Road Layouts 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 in perspective view, our method only requires human annotations for parametric attributes that are cheaper and less ambiguous to obtain. To solve this challenging task, our design is comprised of modules that incorporate inductive biases to learn occlusion-reasoning, geometric transformation and semantic abstraction, where each module may be supervised by appropriately transforming the parametric annotations. We demonstrate how our design choices and proposed deep supervision help achieve meaningful representations and accurate predictions. We validate our approach on two public datasets, KITTI and NuScenes, to achieve state-of-the-art results with considerably less human supervision.

Read more

MM TTA: Multi Modal Test Time Adaptation for 3D Semantic Segmentation

/in /by

MM TTA: Multi Modal Test Time Adaptation for 3D Semantic Segmentation 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 methods usually results in performance instability at test time because multi modal input is not considered jointly. To design a framework that can take full advantage of multi modality, where each modality provides regularized self supervisory signals to other modalities, we propose two complementary modules within and across the modalities. First, Intra modal Pseudolabel Generation (Intra PG) is introduced to obtain reliable pseudo labels within each modality by aggregating information from two models that are both pre trained on source data but updated with target data at different paces. Second, Inter modal Pseudo label Refinement (Inter PR) adaptively selects more reliable pseudo labels from different modalities based on a proposed consistency scheme. Experiments demonstrate that our regularized pseudo labels produce stable self learning signals in numerous multi modal test time adaptation scenarios for 3D semantic segmentation. Visit our project website at https://www.nec labs.com/˜mas/MM TTA

Read more

Learning Cross-Modal Contrastive Features for Video Domain Adaptation

/in /by

Learning Cross-Modal Contrastive Features for Video Domain Adaptation 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 usually associated with multi-modal information, e.g., RGB and optical flow, and thus it remains a challenge to design a better method that considers the cross-modal inputs under the cross-domain adaptation setting. To this end, we propose a unified framework for video domain adaptation, which simultaneously regularizes cross-modal and cross-domain feature representations. Specifically, we treat each modality in a domain as a view and leverage the contrastive learning technique with properly designed sampling strategies. As a result, our objectives regularize feature spaces, which originally lack the connection across modalities or have less alignment across domains. We conduct experiments on domain adaptive action recognition benchmark datasets, i.e., UCF, HMDB, and EPIC-Kitchens, and demonstrate the effectiveness of our components against state-of-the-art algorithms.

Read more

Learning Cross modal Contrastive Features for Video Domain Adaptation

/in /by

Learning Cross modal Contrastive Features for Video Domain Adaptation 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 usually associated with multi modal information, e.g., RGB and optical flow, and thus it remains a challenge to design a better method that considers the cross modal inputs under the cross domain adaptation setting. To this end, we propose a unified framework for video domain adaptation, which simultaneously regularizes cross modal and cross domain feature representations. Specifically, we treat each modality in a domain as a view and leverage the contrastive learning technique with properly designed sampling strategies. As a result, our objectives regularize feature spaces, which originally lack the connection across modalities or have less alignment across domains. We conduct experiments on domain adaptive action recognition benchmark datasets, i.e., UCF, HMDB, and EPIC Kitchens, and demonstrate the effectiveness of our components against state of the art algorithms.

Read more

Fusing the Old with the New: Learning Relative Pose with Geometry-Guided Uncertainty

/in /by

Fusing the Old with the New: Learning Relative Pose with Geometry-Guided Uncertainty 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 under-explored. In this paper, we present a novel framework that involves probabilistic fusion between the two families of predictions during network training, with a view to leveraging their complementary benefits in a learnable way. The fusion is achieved by learning the DNN un- certainty under explicit guidance by the geometric uncertainty, thereby learning to take into account the geometric solution in relation to the DNN prediction. Our network features a self-attention graph neural network, which drives the learning by enforcing strong interactions between different correspondences and potentially modeling complex relationships between points. We propose motion parmeterizations suitable for learning and show that our method achieves state-of-the-art performance on the challenging DeMoN [61] and ScanNet [8] datasets. While we focus on relative pose, we envision that our pipeline is broadly applicable for fusing classical geometry and deep learning.

Read more

Weakly But Deeply Supervised Occlusion Reasoned Parametric Layouts

/in /by

Weakly But Deeply Supervised Occlusion Reasoned Parametric Layouts 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 in perspective view, our method only requires human annotations for parametric attributes that are cheaper and less ambiguous to obtain. To solve this challenging task, our design is comprised of modules that incorporate inductive biases to learn occlusion reasoning, geometric transformation and semantic abstraction, where each module may be supervised by appropriately transforming the parametric annotations. We demonstrate how our design choices and proposed deep supervision help achieve meaningful representations and accurate predictions. We validate our approach on two public datasets, KITTI and NuScenes, to achieve state of the art results with considerably less human supervision.

Read more

Fusing the Old with the New: Learning Relative Pose with Geometry Guided Uncertainty

/in /by

Fusing the Old with the New: Learning Relative Pose with Geometry Guided Uncertainty 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, has as yet remained under explored. In this paper, we present a novel framework that involves probabilistic fusion between the two families of predictions during network training, with a view to leveraging their complementary benefits in a learnable way. The fusion is achieved by learning the DNN uncertainty under explicit guidance by the geometric uncertainty, thereby learning to take into account the geometric solution in relation to the DNN prediction. Our network features a self attention graph neural network, which drives the learning by enforcing strong interactions between different correspondences and potentially modeling complex relationships between points. We propose motion parmeterizations suitable for learning and show that our method achieves state of the art performance on the challenging DeMoN and ScanNet datasets. While we focus on relative pose, we envision that our pipeline is broadly applicable for fusing classical geometry and deep learning.

Read more

Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction

/in /by

Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction 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 of these two by leveraging the strengths of each mitigates the other’s shortcomings. Specifically, we propose a joint narrow and wide baseline based self-improving framework, where on the one hand the CNN-predicted depth is leveraged to perform $ extit(Unknown sysvar: (pseudo))$ RGB-D feature-based SLAM, leading to better accuracy and robustness than the monocular RGB SLAM baseline. On the other hand, the bundle-adjusted 3D scene structures and camera poses from the more principled geometric SLAM are injected back into the depth network through novel wide baseline losses proposed for improving the depth prediction network, which then continues to contribute towards better pose and 3D structure estimation in the next iteration. We emphasize that our framework only requires $ extit(Unknown sysvar: ( unlabeled monocular))$ videos in both training and inference stages, and yet is able to outperform state-of-the-art self-supervised $ extit(Unknown sysvar: (monocular))$ and $ extit(Unknown sysvar: (stereo))$ depth prediction networks (e.g, Monodepth2) and feature based monocular SLAM system (i.e, ORB-SLAM). Extensive experiments on KITTI and TUM RGB-D datasets verify the superiority of our self-improving geometry-CNN framework.

Read more