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

Trong-Tung Nguyen; Jiahan Zhang; Anand Bhattad

cs.CVSep 29, 2026

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

Authors: Trong-Tung Nguyen, Jiahan Zhang, Anand Bhattad

Organizations: Johns Hopkins University

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-aligned physical fields at no additional cost beyond standard rendering. FracGen leverages these maps in two ways: it is trained to jointly predict them alongside RGB video, encouraging the model to capture physical state rather than surface appearance; and it is supervised with physics-informed losses that encourage consistency among the predicted maps. As a result, FracGen captures distinct material-specific fracture behavior without expensive test-time simulation or per-scene tuning, while offering fine-grained control over where an object tears, how fast the crack propagates, and how much deformation precedes failure. We further introduce a benchmark for evaluating the physical plausibility of generated fracture video, and show through extensive experiments that FracGen outperforms existing video generation baselines in both physical and visual fidelity. Results are best viewed in our project website: https://fracgen.github.io/.

Figures & tables

Figure 2 : FracSim generates physically plausible fracture dynamics spanning deformation to structural failure. (a) Alongside RGB video, FracSim outputs FracPhys map. (b) Our damage model enables explicit control over fracture timing under fixed forces and material properties.

Figure 3 : FracGen overview. RGB fracture videos and FracPhys Maps are encoded by a frozen VAE and concatenated along the spatial height dimension for joint generation. Applied loading, material properties and fracture properties provide channel-wise conditioning. The initial object image supplies reference tokens. We adapt the transformer with LoRA using flow-matching supervision and a physics-informed latent consistency regularizer coupling strain, stress, and damage representations.

Panel of Figure 4 — Figure 4 : Qualitative comparison on unseen objects. We compare generated responses to pulling conditions for (a) a cake that tears after limited stretching and (b) a toy that undergoes sustained elongation. FracGen captures these distinct behaviors while better preserving object appearance; competing methods show limited deformation, collapse or changes in object identity. The top row of each panel shows the force conditioning, and frames progress from left to right.

Figure 5 : Generalization to in-the-wild objects . FracGen only needs one single object image and jointly generates the fracture video (left panel) and its FracPhys maps (right panel, 2×2 grid in top-left to bottom-right order: flow, strain, stress, damage), under varying force directions.

Method	Physics Map Pred	FVD $\downarrow$	LPIPS $\downarrow$	PSNR $\uparrow$	SAC $\uparrow$
ForcePrompting-FT ( Gillman et al., 2025 )	$\times$	933.21	0.29	15.93	0.092
PhyCo-FT ( Narayanan et al., 2026 )	$\times$	832.12	0.33	14.18	0.434
CogVideoX-5B-I2V-FT ( Yang et al., 2025 )	$\times$	1533.21	0.32	14.12	0.432
FracGen	$\checkmark$	266.17	0.15	21.19	0.946

Table 1: Quantitative results on held-out test set. All baselines are fine-tuned on the same dataset.

Figure 6 : Controlled deformation and tearing. (i) Generated sequences for objects with low- and high-stretch fracture settings. (ii) Changing material stiffness for the same object produces different deformation and tearing behavior.

Video Quality & Physics Alignment
Metric	Stage 1	Stage 2	Stage 3
	( $\times$ FracPhys)	( $\checkmark$ , w/o Eq. 10 )	( $\checkmark$ , w. Eq. 10 )
FVD $\downarrow$	298.04	289.65	266.17
LPIPS $\downarrow$	0.1555	0.1550	0.1502
PSNR $\uparrow$	20.73	20.82	21.19
SAC $\uparrow$	0.9460	0.9393	0.9462

Table 2: Ablation: video quality , physics alignment , and evaluation of FracPhys map prediction (MSE). Stage 1 has no physics map; hence DPA and FracPhysMap evaluation are not applicable.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

	Low-stretch objects	High-stretch objects
Constitutive model	Fixed corotated	Neo-Hookean
Young modulus $E$	$\{2\times 10^{3}$ , $6\times 10^{3}$ , $10^{4}\}$	$\{2\times 10^{4}$ , $6\times 10^{4}$ , $10^{5}\}$
Poisson ratio $\nu$	$\{0.2,0.25,0.3\}$	$\{0.45,0.47,0.49\}$
Onset, critical stretch $(\lambda_{\text{on}}$ , $\lambda_{\text{cr}}$ )	$\{(1.5,2.3),(2.0,3.0)\}$	$\{(2.6,3.0),(3.0,3.3)\}$
RPIC damping / grid velocity decay	$0.5$ / $0.9995$	$0.005$ / $0.9998$
Grip speed $v$	$\{0.5,0.6,0.7,0.8\}$	$\{0.6,0.8,1.2,1.4\}$

Appendix

Table 3: Per-class simulation parameters.

Figure 7 : Ten objects used for simulation. First 3 of each category is then used for training while last two are used for testing and benchmarking.

Figure 8 : More ten random objects used for testing FracGen generalization. Results can be found on our website.

Figure 9 : We show illustration of using point tracks to extract principal stretching axis.

Figure 10 : Screenshot of annotation tool to provide physics condition for FracGen

Figure 11 : Ablation Studies. Comparison results for ablating the effect of physics map prediction and physics consistency loss.

Method	FVD $\downarrow$	LPIPS $\downarrow$	PSNR $\uparrow$	SAC $\uparrow$
ForcePrompting	1226.32	0.32	15.07	0.075
ForcePrompting-FT	933.21	0.29	15.93	0.092
PhyCo	1595.01	0.38	12.51	0.415
PhyCo-FT	832.12	0.33	14.18	0.434
CogVideoX-5B-I2V	1844.92	0.34	13.78	0.470
CogVideoX-5B-I2V-FT	1533.21	0.32	14.12	0.432

Appendix

Table 4 : Comparison of baselines with their zero-shot and fine-tuned (-FT) version.

Explore similar work

Apr 30, 2026cs.CV

PhyCo: Learning Controllable Physical Priors for Generative Motion

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation. Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback. This combination enables a generative model to produce physically consistent and controllable outputs through variations in physical attributes-without any simulator or geometry reconstruction at inference. On the Physics-IQ benchmark, PhyCo significantly improves physical realism over strong baselines, and human studies confirm clearer and more faithful control over physical attributes. Our results demonstrate a scalable path toward physically consistent, controllable generative video models that generalize beyond synthetic training environments.

Sriram Narayanan, Ziyu Jiang, Srinivasa Narasimhan +1

1Carnegie Mellon University · 2NEC Labs America · 3UC San Diego

Generative Video Models Video Diffusion Models Human Motion Generation Physics Simulation Synthetic Training Data Supervised Finetuning

Ask PDF

Jul 21, 2026cs.CV

DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking

Video generation models achieve high visual quality but often struggle to generate physics-aware videos. Unlike rigid-body motion, which can be described by explicit trajectories or formulas, complex deformation dynamics remain challenging to synthesize. We observe that a lack of physical reasoning for localizing dynamic areas allows irrelevant regions to dilute the model's attention, leading to generation failure. In this paper, we propose DeforM, a reasoning-guided image-to-video generation framework that directs the model's focus toward physics-critical regions. To reason about and localize these critical regions, we introduce a VLM-guided physical reasoning module, DeforM-Reason, to identify target objects and generate spatial-temporal masks. For physical guidance, we develop two alternative strategies: DeforM-Free for training-free mechanism analysis and DeforM-Injection as a powerful training-based generator. Experimental results demonstrate that DeforM improves the realism of generated deformation scenarios, outperforming baseline models in both visual quality and physical consistency.

Yunyi Li, Yu Qiao, Yaohui Wang +1

Shanghai Artificial Intelligence Laboratory, Shanghai, China

Generative Video Models Video Generation Human Motion Generation Deformable Physics-Aware Models

Ask PDF

Jul 26, 2026cs.CV

VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation

Modern video generation models can synthesize visually compelling and temporally coherent clips, yet controlling their physical behavior remains difficult with standard text and image conditions. The core challenge is a conditioning bottleneck: material response, contact interaction, deformation, and motion trajectory are continuous and relational physical cues that are hard to specify exhaustively in language but can be demonstrated naturally by video. We propose VIPER, a Visual In-Context Physics Reasoning framework for reference-guided image-to-video generation. Given a target image, a brief target prompt, and a reference video, VIPER treats the reference as a dense visual demonstration of the desired physical process rather than an appearance template. It uses a Multimodal Large Language Model (MLLM) to extract reference-derived physical cues and guide a pretrained image-to-video generator through a hierarchical training strategy, enabling physical behavior transfer while preserving the visual prior of the base generator. To support this setting, we construct VIPER-19K, a curated dataset with material, trajectory, and physical-impact annotations, together with filtered reference-target pairs. Experiments on an unseen validation set show that VIPER achieves stronger reference-video physical similarity and higher human preference than representative video generation and video-as-prompt baselines, while maintaining competitive general video quality. Qualitative results further demonstrate that VIPER can transfer reference-derived physical behavior to new target scenes without requiring carefully engineered prompts.

Tianxiao Chen, Hanmo Chen, Huajin Chen +3

Zhejiang University · vivo BlueImage Lab, vivo Mobile Communication Co., Ltd.

Generative Video Models Similarity and Metrics

Ask PDF