arXiv Computer Vision October 22, 2026 By Bei Huang, Yixin Chen, Hongbin Zha, Yuru Pei, Siyuan Huang

AutoPhyX: Automatic Text-Condition Physics Property Generation

Read the original on arXiv Computer Vision →

AutoPhyX is a text-conditioned framework that predicts spatially-varying physical properties for 4D physical simulation. It uses a novel part-controllable data generation pipeline to create fine-grained, semantically distinct 3D assets paired with diverse parameters and text descriptions. The model employs cross-modal modulation to dynamically adjust visual features based on text, enabling accurate, physically plausible parameter assignment across various 3D representations in a single forward pass.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

6d ago

PhysCreator: Creating Physically-Attributed 3D Assets at Will

arXiv:2610.34473v1 Announce Type: new Abstract: Significant advancements in 3D asset creation have enabled high-fidelity 3D generation from images. However, most existing representations remain inher...

By Shiyan Zheng, Ming Li, Lei Han, Xiangyu Xu

llms diffusion efficiency multimodal

Hugging Face Trending Papers

Jun 22

Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics

Synthesizing realistic Human-Object Interactions (HOI) is critical for creating embodied avatars and functional virtual environments. However, current data-driven approaches primarily rely on motion capture datasets, which are expensive to scale and limited in functional diversity.

diffusion reinforcement-learning robotics

arXiv AI

Jun 4

UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD

arXiv:2606. 05058v1 Announce Type: cross Abstract: Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models.

By Jingyuan Chen, Sheng Jin, Haopeng Sun, Wentao Liu, Chen Qian

llms nlp multimodal benchmarks

Hugging Face Trending Papers

Jul 21

Learning Explicit Physical Parameter Control and Benchmarking for Video Generation

Recent advances in image-to-video generation have improved visual realism, making physically grounded and controllable dynamics an important step toward future world simulation. Current models often generate plausible motion, but it is not reliably governed by explicit physical causes, and instance-level constraints can leak or become entangled in multi-object interactions.

diffusion benchmarks safety

arXiv AI

Jul 3

Learning 3D-Gaussian Simulators from RGB Videos

arXiv:2503. 24009v3 Announce Type: replace-cross Abstract: Realistic simulation is critical for applications ranging from robotics to animation.

By Mikel Zhobro, Andreas Ren\'e Geist, Georg Martius

llms robotics

arXiv Computer Vision

Oct 19

FlexPart: Text-Controlled Semantics-Aware 3D Part Segmentation at Flexible Granularity

FlexPart is a new framework that enables text‑controlled, semantics‑aware 3D mesh segmentation at any desired granularity. It introduces a holistic control prompt that combines part names with location and shape clauses, and uses a Vision‑Language Model pipeline to generate a large multi‑granularity dataset. The model produces a view‑independent part‑identity field in 3D space, and an inference‑time VLM planner can auto‑complete descriptive clauses from 2D renderings, allowing users to specify parts with ordinary words. FlexPart outperforms strong baselines by up to 22% in mIoU on its benchmark and improves selective segmentation by 35% over click‑driven methods.

By Yiqun Zhao, Jiachen Xu, Yihao Zhi, Yunfei Zhao, Zibo Zhao, Xintong Han, Chunchao Guo, Shenghua Gao

llms computer-vision multimodal