Conditional Image-to-Video Generation with Latent Flow Diffusion Models Conditional image-to-video (cI2V) generation aims to synthesize a new plausible video starting from an image (e.g., a person’s face) and a condition (e.g., an action class label like smile). The key challenge of the cI2V task lies in the simultaneous generation of realistic spatial appearance and temporal dynamics corresponding to the given image and condition. In this paper, we propose an approach for cI2V using novel latent flow diffusion models (LFDM) that synthesize an optical flow sequence in the latent space based on the given condition to warp the given image. Compared to previous direct-synthesis-based works, our proposed LFDM can better synthesize spatial details and temporal motion by fully utilizing the spatial content of the given image and warping it in the latent space according to the generated temporally-coherent flow. The training of LFDM consists of two separate stages: (1) an unsupervised learning stage to train a latent flow auto-encoder for spatial content generation, including a flow predictor to estimate latent flow between pairs of video frames, and (2) a conditional learning stage to train a 3D-UNet-based diffusion model (DM) for temporal latent flow generation. Unlike previous DMs operating in pixel space or latent feature space that couples spatial and temporal information, the DM in our LFDM only needs to learn a low-dimensional latent flow space for motion generation, thus being more computationally efficient. We conduct comprehensive experiments on multiple datasets, where LFDM consistently outperforms prior arts. Furthermore, we show that LFDM can be easily adapted to new domains by simply finetuning the image decoder. Our code is available at https://github.com/nihaomiao/CVPR23_LFDM.
Generative Models are a class of models designed to generate new data samples that resemble a given training dataset. These models learn the underlying patterns and structures present in the training data and can then generate new, similar data points. The goal of generative models is to capture the distribution of the training data and generate realistic samples that share characteristics with the original dataset.
AE-StyleGAN: Improved Training of Style-Based Auto-Encoders StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad hoc after the generator is trained in a two-stage fashion. In this paper, we focus on style-based generators asking a scientific question: Does forcing such a generator to reconstruct real data lead to more disentangled latent space and make the inversion process from image to latent space easy? We describe a new methodology to train a style-based autoencoder where the encoder and generator are optimized end-to-end. We show that our proposed model consistently outperforms baselines in terms of image inversion and generation quality. Supplementary, code, and pretrained models are available on the project website.
Learning Gibbs-Regularized Pushforward Density Estimators with a Symmetric KL Objective 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 that usually bears no resemblance to the true generation process, which is most often unobserved or exceedingly difficult to model. Consider image generation: although it is plausiblee.g., from biological argumentsthat convolutional neural networks constitute a good class of image classifiers, claiming CNNs are inherently well-suited to image generation is harder to justify. Likewise, it is clear that regularizing the discriminator is necessary to prevent trivial solutions; although recent methods have seen some success in applying generic smoothness regularizers to the discriminator [1, 5, 12], it is not obvious how to impose domain-specific structure on the discriminator in an optimal way
4 Independence Way, Suite 200
Princeton, NJ 08540
San Jose Office
2033 Gateway Place, Suite 200
San Jose, CA 95110
NEC Laboratories America, Inc. (NEC Labs) is the US-based center for NEC Corporation’s global network of corporate research laboratories. Our diverse research groups collaborate with industry, academia and governments to provide disruptive solutions to complex problems. A leader in the integration of IT and network technologies with more than 100 years of expertise, NEC provides a combination of products and solutions that cross-utilize the company’s experience and global resources to meet the complex and ever-changing needs of its customers.
Read Our Blog Posts
- Apply for a Summer 2024 Internship
- Unearthing Nature’s Orchestra – How Fiber Optic Cables Can Hear Cicada Secrets
- NEC Labs America Team Heading to NeurIPS23 in New Orleans
- Sarper Ozharar Receives Award from Koç University
- Meet the NEC Labs America Intern Helping to Make Autonomous Vehicles Safer and More Secure
- AI/Fiber-Optic Combo Poised To Improve Telecommunications
- Industrial Labs to Drive Disruptive Innovation for the Fourth Industrial Revolution
- A New Hope: AI Research is Conquering Today’s Computer Vision Plateau
- NEC Labs America’s Time Series Data Research Drives Space Systems Innovation
- Next-Generation Computing Finally Sees Light
- AI/Fiber-Optic Combo Poised To Improve Telecommunications
- Using AI To Safely Put The First Woman On The Moon
- Our AI Research Contributing to NASA’s Artemis Space Program
- NEC provides AI-based traffic monitoring system with fiber-optic sensing technology for NEXCO CENTRAL
- Beyond Communication: Telecom Fiber Networks for Rain Detection and Classification