Copertina

IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Parker, Li, Chenxin, Li, Zhengxin, Wu, Yipeng, Li, Wuyang, Yang, Zhiqin, Zhang, Zhenyuan, Lin, Yunlong, Han, Sirui, Feng, Brandon Y.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction
di: Liu, Hengyu, et al.
Pubblicazione: (2024)

TensoIR: Tensorial Inverse Rendering
di: Jin, Haian, et al.
Pubblicazione: (2023)

UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video
di: Lin, Chih-Hao, et al.
Pubblicazione: (2023)

GUS-IR: Gaussian Splatting with Unified Shading for Inverse Rendering
di: Liang, Zhihao, et al.
Pubblicazione: (2024)

SAR-GS: Gaussian Splatting based SAR Images Rendering and Target Reconstruction
di: Li, Aobo, et al.
Pubblicazione: (2025)

GS-IR: 3D Gaussian Splatting for Inverse Rendering
di: Liang, Zhihao, et al.
Pubblicazione: (2023)

JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration
di: Lin, Yunlong, et al.
Pubblicazione: (2025)

IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images
di: Lin, Chih-Hao, et al.
Pubblicazione: (2024)

DiffuSyn Bench: Evaluating Vision-Language Models on Real-World Complexities with Diffusion-Generated Synthetic Benchmarks
di: Zhou, Haokun, et al.
Pubblicazione: (2024)

Endora: Video Generation Models as Endoscopy Simulators
di: Li, Chenxin, et al.
Pubblicazione: (2024)

MemFly: On-the-Fly Memory Optimization via Information Bottleneck
di: Zhang, Zhenyuan, et al.
Pubblicazione: (2026)

EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting
di: Li, Chenxin, et al.
Pubblicazione: (2024)

Harnessing Lightweight Transformer with Contextual Synergic Enhancement for Efficient 3D Medical Image Segmentation
di: Liu, Xinyu, et al.
Pubblicazione: (2026)

Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation
di: Ling, Lu, et al.
Pubblicazione: (2025)

SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering
di: Sun, Hanxiao, et al.
Pubblicazione: (2025)

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
di: Li, Lei, et al.
Pubblicazione: (2024)

Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification
di: Li, Ming, et al.
Pubblicazione: (2024)

CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and Authenticity
di: Wei, Xuefeng, et al.
Pubblicazione: (2026)

GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
di: Shi, Yahao, et al.
Pubblicazione: (2023)

TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering
di: Gui, Rui, et al.
Pubblicazione: (2025)

LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control
di: Qu, Delin, et al.
Pubblicazione: (2024)

SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
di: Li, Yue, et al.
Pubblicazione: (2025)

GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models
di: Xie, Qinghongbing, et al.
Pubblicazione: (2025)

Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
di: Pan, Panwang, et al.
Pubblicazione: (2025)

RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
di: Lin, Jingru, et al.
Pubblicazione: (2025)

AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding
di: Wang, Yonghui, et al.
Pubblicazione: (2024)

RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding
di: Xiao, Xi, et al.
Pubblicazione: (2025)

FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
di: Yang, Zhiqin, et al.
Pubblicazione: (2025)

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
di: Lin, Jingli, et al.
Pubblicazione: (2025)

WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Rendering
di: Han, Yuxuan, et al.
Pubblicazione: (2025)

Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble
di: Duan, Lin, et al.
Pubblicazione: (2025)

SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
di: Jia, Baoxiong, et al.
Pubblicazione: (2024)

NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving
di: Tian, Kexin, et al.
Pubblicazione: (2025)

Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline
di: Huang, Yuzhi, et al.
Pubblicazione: (2025)

EventVL: Understand Event Streams via Multimodal Large Language Model
di: Li, Pengteng, et al.
Pubblicazione: (2025)

Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes
di: Choi, JunYong, et al.
Pubblicazione: (2025)

UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation
di: Wu, Shuang, et al.
Pubblicazione: (2024)

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
di: Chow, Wei, et al.
Pubblicazione: (2025)

VULCA-Bench: A Multicultural Vision-Language Benchmark for Evaluating Cultural Understanding
di: Yu, Haorui, et al.
Pubblicazione: (2026)

Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving
di: Gao, Haoxiang, et al.
Pubblicazione: (2025)