Related papers: Video Generation Models as World Models: Efficient…
World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising basis for such simulators because they can generate diverse…
Three-dimensional content generation has progressed from producing isolated, visually plausible shapes to constructing structured assets that can be deployed in real-time interactive environments. This trajectory is driven by converging…
Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory for consistency, or iterative 3D reconstruction and…
Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…
The rapid advancement of Artificial Intelligence Generated Content (AIGC) has revolutionized video generation, enabling systems ranging from proprietary pioneers like OpenAI's Sora, Google's Veo3, and Bytedance's Seedance to powerful…
Video generation is an interesting problem in computer vision. It is quite popular for data augmentation, special effect in move, AR/VR and so on. With the advances of deep learning, many deep generative models have been proposed to solve…
We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation. Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without…
Diffusion models have emerged as a powerful new family of deep generative models with record-breaking performance in many applications, including image synthesis, video generation, and molecule design. In this survey, we provide an overview…
Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further…
Generative artificial intelligence has recently progressed from static image and video synthesis to 3D content generation, culminating in the emergence of 4D generation-the task of synthesizing temporally coherent dynamic 3D assets guided…
We present a novel method for generating geometrically realistic and consistent orbital videos from a single image of an object. Existing video generation works mostly rely on pixel-wise attention to enforce view consistency across frames.…
Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small…
Video generation has seen remarkable progress thanks to advancements in generative deep learning. However, generating long sequences remains a significant challenge. Generated videos should not only display coherent and continuous movement…
The video generation field has witnessed rapid improvements with the introduction of recent diffusion models. While these models have successfully enhanced appearance quality, they still face challenges in generating coherent and natural…
We tackle the problem of learning complex, general behaviors directly in the real world. We propose an approach for robots to efficiently learn manipulation skills using only a handful of real-world interaction trajectories from many…
Generating long, high-quality videos remains a challenge due to the complex interplay of spatial and temporal dynamics and hardware limitations. In this work, we introduce MaskFlow, a unified video generation framework that combines…
Generative world models have become essential data engines for autonomous driving, yet most existing efforts focus on videos or occupancy grids, overlooking the unique LiDAR properties. Extending LiDAR generation to dynamic 4D world…
Over the past decade, deep learning models have exhibited considerable advancements, reaching or even exceeding human-level performance in a range of visual perception tasks. This remarkable progress has sparked interest in applying deep…
Yume aims to use images, text, or videos to create an interactive, realistic, and dynamic world, which allows exploration and control using peripheral devices or neural signals. In this report, we present a preview version of \method, which…
Due to the difficulty of acquiring extensive real-world data, robot simulation has become crucial for parallel training and sim-to-real transfer, highlighting the importance of scalable simulated robotic tasks. Foundation models have…