Signals 4 · free daily AI digest

FracGen: Learning How Objects Stretch and Tear with Physics-Informed Video Generation

Paper recorded by Signals 4 on 2026-09-29 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-29 on arXiv · recorded by Signals 4 on 2026-09-30

Category: cs.CV · 计算机视觉 · first seen 2026-09-30

Abstract

We introduce FracGen, a fracture-aware video generation model that produces plausible, controllable fracture dynamics from a single image of an intact object, conditioned on physics signals. To train FracGen, we build FracSim, a fracture-aware simulation framework that augments material point method (MPM) simulation with a continuum damage model, producing paired fracture videos and dense, pixel-a

Read on arXiv →

#8 most recent of 357 cs.CV papers we have recorded · ↑ newer: PowerSim: Differentiable Physics Simulation and Rendering with Power D · ↓ older: LIFT: Layout-In-Future Video Generation under Large Viewpoint Change v
Cite this page: FracGen: Learning How Objects Stretch and Tear with Physics-Informed Video Generation: the #8 most recent of 357 cs.CV papers we have recorded (as of 2026-09-29). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/fracgen-learning-how-objects-stretch-and-tear-with-physics-informed-video-genera.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions