paper-with-me

홈 › Papers

Learning 3D Particle-based Simulators from RGB-D Videos

2023-12-08 · William F. Whitney, Tatiana Lopez-Guevara, Tobias Pfaff, Yulia Rubanova, Thomas Kipf, Kimberly Stachenfeld, Kelsey R. Allen

Realistic simulation is critical for applications ranging from robotics to animation. Traditional analytic simulators sometimes struggle to capture sufficiently realistic simulation which can lead to problems including the well known "sim-to-real" gap in robotics. Learned simulators have emerged as an alternative for better capturing real-world physical dynamics, but require access to privileged ground truth physics information such as precise object geometry or particle tracks. Here we propose a method for learning simulators directly from observations. Visual Particle Dynamics (VPD) jointly learns a latent particle-based representation of 3D scenes, a neural simulator of the latent particle dynamics, and a renderer that can produce images of the scene from arbitrary views. VPD learns end to end from posed RGB-D videos and does not require access to privileged information. Unlike existing 2D video prediction models, we show that VPD's 3D structure enables scene editing and long-term predictions. These results pave the way for downstream applications ranging from video editing to robotic planning.

📄 PDF Abstract BibTeX arXiv:2312.05359

Code (0)

등록된 구현이 없습니다.

Tasks

Video EditingVideo Prediction

Similar Papers 제목 키워드 기반

Learning a Particle Dynamics Model with Real-world Videos

2026-05-22 · Chanho Kim, Suhas V. Sumukh, Li Fuxin arxiv

Data-driven learning approaches for physics simulation, sometimes referred to as world models, have emerged as promising alternatives to traditional physics simulators due to their differentiable nature. Prior work has d…

Point Clouds

Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos

2025-06-18 · Kaifeng Zhang, Baoyu Li, Kris Hauser, Yunzhu Li

Modeling the dynamics of deformable objects is challenging due to their diverse physical properties and the difficulty of estimating states from limited visual information. We address these challenges with a neural dynam…

Object

Bridged SBI: Correcting Biased Low-Fidelity Posteriors for Cost-Efficient High-Fidelity Inference

2026-06-08 · Gahee Kim, Yuki Kadokawa, Sandro M. Alcantara Tacora, Taro Abe 외 arxiv

Accurate calibration of particle-based simulators is crucial for robotic earthwork simulation, but analytical calibration is challenging due to this task's highly nonlinear particle dynamics and the black-box nature of c…

Physically Accurate Rigid-Body Dynamics in Particle-Based Simulation

2026-03-15 · Ava Abderezaei, Nataliya Nechyporenko, Joseph Miceli, Gilberto Briscoe-Martinez 외 arxiv

Robotics demands simulation that can reason about the diversity of real-world physical interactions, from rigid to deformable objects and fluids. Current simulators address this by stitching together multiple subsolvers …

Computational Efficiency

Learning 3D-Gaussian Simulators from RGB Videos

2025-03-31 · Mikel Zhobro, Andreas René Geist, Georg Martius

Learning physics simulations from video data requires maintaining spatial and temporal consistency, a challenge often addressed with strong inductive biases or ground-truth 3D information -- limiting scalability and gene…

Inverse Rendering