Related papers: OrthoPhys: Physically Plausible Video Generation w…
Recent advances in diffusion-based video generation have achieved remarkable visual realism but still struggle to obey basic physical laws such as gravity, inertia, and collision. Generated objects often move inconsistently across frames,…
Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a real-time framework for infinite, 3D-consistent video…
Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. Bridging generation and novel view…
Recent advances in video generation have enabled the synthesis of high-quality and visually realistic clips using diffusion transformer models. However, most existing approaches operate purely in the 2D pixel space and lack explicit…
We introduce a method to synthesize animator guided human motion across 3D scenes. Given a set of sparse (3 or 4) joint locations (such as the location of a person's hand and two feet) and a seed motion sequence in a 3D scene, our method…
Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to enable precise object motion control through explicitly…
Recent advances in image and video generation raise hopes that these models possess world modeling capabilities, the ability to generate realistic, physically plausible videos. This could revolutionize applications in robotics, autonomous…
Humans can easily segment moving objects without knowing what they are. That objectness could emerge from continuous visual observations motivates us to model grouping and movement concurrently from unlabeled videos. Our premise is that a…
This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physically unrealistic motions due to limited contact modeling, typically restricted to hands, in…
We present a method for text-driven perpetual view generation -- synthesizing long-term videos of various scenes solely, given an input text prompt describing the scene and camera poses. We introduce a novel framework that generates such…
Existing 4D synthesis methods primarily focus on object-level generation or dynamic scene synthesis with limited novel views, restricting their ability to generate multi-view consistent and immersive dynamic 4D scenes. To address these…
Video generation models have advanced significantly, yet they still struggle to synthesize complex human movements due to the high degrees of freedom in human articulation. This limitation stems from the intrinsic constraints of pixel-only…
Realistic object interactions are crucial for creating immersive virtual experiences, yet synthesizing realistic 3D object dynamics in response to novel interactions remains a significant challenge. Unlike unconditional or text-conditioned…
Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses rigidly bind motion to the driving viewpoint, precluding…
Current video diffusion models generate visually compelling content but often violate basic laws of physics, producing subtle artifacts like rubber-sheet deformations and inconsistent object motion. We introduce a frequency-domain physics…
Text- and image-conditioned video generation models have achieved strong visual fidelity and temporal coherence, but they often fail to generate motion governed by kinematic and geometric constraints. In these settings, object parts must…
We investigate how to enhance the physical fidelity of video generation models by leveraging synthetic videos derived from computer graphics pipelines. These rendered videos respect real-world physics, such as maintaining 3D consistency,…
Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme…
While current methods have shown promising progress on estimating 3D human motion from monocular videos, their motion estimates are often physically unrealistic because they mainly consider kinematics. In this paper, we introduce…
Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible motion-sound relations remains challenging. Existing methods often produce object motions…