Cover Image

Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Wenqiao, Gu, Yao, Chen, Xintao, Xu, Xiaohao, Hu, Ming, Huang, Xiaonan, Wu, Yingna
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-turn Physics-informed Vision-language Model for Physics-grounded Anomaly Detection
by: Gu, Yao, et al.
Published: (2026)

Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representation
by: Zheng, Bozhong, et al.
Published: (2025)

Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided Alignment
by: Chen, Xintao, et al.
Published: (2025)

Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning
by: Xu, Xiaohao, et al.
Published: (2024)

Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties
by: Li, Wenqiao, et al.
Published: (2024)

Photorealistic Phantom Roads in Real Scenes: Disentangling 3D Hallucinations from Physical Geometry
by: Nguyen, Hoang, et al.
Published: (2025)

Breaking the Rigid Prior: Towards Articulated 3D Anomaly Detection
by: Gan, Jinye, et al.
Published: (2026)

A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect
by: Cao, Yunkang, et al.
Published: (2024)

Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration
by: Wang, Jun, et al.
Published: (2026)

Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmark
by: Cao, Yunkang, et al.
Published: (2025)

Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM
by: Zhang, Huaxin, et al.
Published: (2024)

Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
by: Zhang, Huaxin, et al.
Published: (2024)

GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection
by: Zhang, Huaxin, et al.
Published: (2024)

PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing
by: Xu, Ruihang, et al.
Published: (2026)

Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images
by: Tan, Chuangchuang, et al.
Published: (2025)

Is Your LiDAR Placement Optimized for 3D Scene Understanding?
by: Li, Ye, et al.
Published: (2024)

AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection
by: Gu, Zhaopeng, et al.
Published: (2025)

MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction
by: Xu, Xiaohao, et al.
Published: (2024)

Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
by: Cao, Yunkang, et al.
Published: (2023)

GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning
by: Miao, Deshui, et al.
Published: (2026)

Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection
by: Tao, Chenchen, et al.
Published: (2024)

LogiCode: an LLM-Driven Framework for Logical Anomaly Detection
by: Zhang, Yiheng, et al.
Published: (2024)

DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
by: Li, Xiangtai, et al.
Published: (2025)

DMAD: Dual Memory Bank for Real-World Anomaly Detection
by: Hu, Jianlong, et al.
Published: (2024)

When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills
by: Wang, Yunfei, et al.
Published: (2026)

Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection
by: Wang, Chengjie, et al.
Published: (2024)

OpenGround: Active Cognition-based Reasoning for Open-World 3D Visual Grounding
by: Huang, Wenyuan, et al.
Published: (2025)

MagiC: Evaluating Multimodal Cognition Toward Grounded Visual Reasoning
by: Wu, Chengfei, et al.
Published: (2025)

CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection
by: Yuan, Zhipeng, et al.
Published: (2025)

PhyGround: Benchmarking Physical Reasoning in Generative World Models
by: Lin, Juyi, et al.
Published: (2026)

EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs
by: Dai, Yang, et al.
Published: (2026)

RGBT-Ground Benchmark: Visual Grounding Beyond RGB in Complex Real-World Scenarios
by: Zhao, Tianyi, et al.
Published: (2025)

Sparse Reasoning is Enough: Biological-Inspired Framework for Video Anomaly Detection with Large Pre-trained Models
by: Huang, He, et al.
Published: (2025)

BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding
by: Li, Hongbing, et al.
Published: (2026)

Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World
by: Huang, Yuzhi, et al.
Published: (2026)

Grounding Video Reasoning in Physical Signals
by: Osmanli, Alibay, et al.
Published: (2026)

VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning
by: Ji, Yuheng, et al.
Published: (2025)

A Recover-then-Discriminate Framework for Robust Anomaly Detection
by: Xing, Peng, et al.
Published: (2024)

Towards Transferable Targeted 3D Adversarial Attack in the Physical World
by: Huang, Yao, et al.
Published: (2023)

PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models
by: Mak, Chak-Wing, et al.
Published: (2026)