CORTEXA
← Browse
arxivcs.CV2026-07-21

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

Yunyi Li, Yu Qiao, Yaohui Wang, Xinyuan Chen

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.

View free PDFSource page

Related papers

arxivcs.CV2026-07-16

Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning

Kazi Sajeed Mehrab, Hani Alomari, Najibul Haque Sarker, Chia-Wei Tang, Zaber Ibn Abdul Hakim, Anuj Karpatne, et al.

Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a part rather than the object. We trace this to a missing object-part hierarchy, since parts are localized in the same single step used for o…

View free PDFSource page
arxivcs.AIcs.CVcs.MM2026-07-20

OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment

Wenxiao Fan, Hang Yin, Kan Li

Multimodal large language models (MLLMs) still struggle with spatial reasoning that requires perspective transformation. In particular, they often rely on camera-centric cues rather than reasoning from the reference object's viewpoint, leading to systematic errors in non-camera r…

View free PDFSource page
arxivcs.CVcs.AI2026-07-17

PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation

Qirui Li, Jinkun Hao, Yibo Li, Ran Yi, Paul L. Rosin, Yu-Kun Lai

Recent advances in physics-grounded video generation leverage physics simulation as a physical prior to guide video synthesis toward physically plausible outcomes. The simulation process is controlled by physical specifications, which are typically generated by a vision-language…

View free PDFSource page
arxivcs.CV2026-07-17

Physics-aware Masked Diffusion-based Flood Simulation for Urban Fisheye Disaster Detection

Sodtavilan Odonchimed, Tsogt Enkhbayar, Oyunzul Munkhtamga, Munkhjargal Gochoo

Physical simulations that predict the behavior of urban disasters, such as climate-related flooding, play a crucial role in disaster prevention and the development of anomaly detection models. However, the severe shortage of flood data in real-world environments, combined with th…

View free PDFSource page
arxivcs.CV2026-07-17

Event3R: Asynchronous-to-Global 3D Reconstruction from Event Camera via Spatial-Temporal Feature Aggregation

Jian Huang, Haotian Shen, Xinhao Lou, Chengrui Dong, Wenpu Li, Peidong Liu

Robust 3D reconstruction is essential for robotics and embodied perception. Recent feed-forward approaches such as DUSt3R have demonstrated impressive progress in dense 3D reconstruction from RGB images, achieving global geometric consistency and strong generalization. However, e…

View free PDFSource page
arxivcs.CV2026-07-20

ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning

Ting Huang, Zhenyu Zhang, Wenyuan Huang, Jian Yang, Hao Tang

Video spatial reasoning is essential for navigation-oriented perception and long-video question answering, where models must infer spatial relations across long horizons under changing viewpoints. However, existing multimodal large language models (MLLMs) remain largely semantic-…

View free PDFSource page