paper-with-me

Papers

Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach

2025-02-05 · Yunuo Chen, Junli Cao, Anil Kag, Vidit Goel, Sergei Korolev, Chenfanfu Jiang, Sergey Tulyakov, Jian Ren

We present a novel video generation framework that integrates 3-dimensional geometry and dynamic awareness. To achieve this, we augment 2D videos with 3D point trajectories and align them in pixel space. The resulting 3D-aware video dataset, PointVid, is then used to fine-tune a latent diffusion model, enabling it to track 2D objects with 3D Cartesian coordinates. Building on this, we regularize the shape and motion of objects in the video to eliminate undesired artifacts, \eg, nonphysical deformation. Consequently, we enhance the quality of generated RGB videos and alleviate common issues like object morphing, which are prevalent in current video models due to a lack of shape awareness. With our 3D augmentation and regularization, our model is capable of handling contact-rich scenarios such as task-oriented videos. These videos involve complex interactions of solids, where 3D information is essential for perceiving deformation and contact. Furthermore, our model improves the overall quality of video generation by promoting the 3D consistency of moving objects and reducing abrupt changes in shape and motion.

📄 PDF Abstract BibTeX arXiv:2502.03639

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

From Generated Human Videos to Physically Plausible Robot Trajectories

2025-12-04 · James Ni, Zekai Wang, Wei Lin, Amir Bar 외 arxiv

Video generation models are rapidly improving in their ability to synthesize human actions in novel contexts, holding the potential to serve as high-level planners for contextual robot control. To realize this potential,…

Zero-shot GeneralizationReinforcement LearningVideo Generation

Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench

2025-12-02 · Lanxiang Hu, Abhilash Shankarampeta, Yixin Huang, Zilin Dai 외 arxiv

The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for accurate physical outcome modeling under diverse conditions. …

Video Generation

Geometry-aware 4D Video Generation for Robot Manipulation

2025-07-01 · Zeyi Liu, Shuang Li, Eric Cousineau, Siyuan Feng 외

Understanding and predicting the dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in …

Robot ManipulationVideo Generation

Synthetic Video Enhances Physical Fidelity in Video Synthesis

2025-03-26 · Qi Zhao, Xingyu Ni, Ziyu Wang, Feng Cheng 외

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 maintainin…

Video Generation

MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics

2026-06-01 · Žiga Kovačič, Kevin Ellis arxiv

To study the ability to infer physical dynamics from videos and extrapolate them forward in time, we assemble a dataset of 2D Material Point Method (MPM) physical simulations covering rich physical phenomena such as defo…

Physical SimulationsCode Generation