|国家预印本平台
首页|IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering

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

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

来源:Arxiv_logoArxiv
英文摘要

Vision-language models (VLMs) excel at descriptive tasks, but whether they truly understand scenes from visual observations remains uncertain. We introduce IR3D-Bench, a benchmark challenging VLMs to demonstrate understanding through active creation rather than passive recognition. Grounded in the analysis-by-synthesis paradigm, IR3D-Bench tasks Vision-Language Agents (VLAs) with actively using programming and rendering tools to recreate the underlying 3D structure of an input image, achieving agentic inverse rendering through tool use. This "understanding-by-creating" approach probes the tool-using generative capacity of VLAs, moving beyond the descriptive or conversational capacity measured by traditional scene understanding benchmarks. We provide a comprehensive suite of metrics to evaluate geometric accuracy, spatial relations, appearance attributes, and overall plausibility. Initial experiments on agentic inverse rendering powered by various state-of-the-art VLMs highlight current limitations, particularly in visual precision rather than basic tool usage. IR3D-Bench, including data and evaluation protocols, is released to facilitate systematic study and development of tool-using VLAs towards genuine scene understanding by creating.

Parker Liu、Chenxin Li、Zhengxin Li、Yipeng Wu、Wuyang Li、Zhiqin Yang、Zhenyuan Zhang、Yunlong Lin、Sirui Han、Brandon Y. Feng

计算技术、计算机技术

Parker Liu,Chenxin Li,Zhengxin Li,Yipeng Wu,Wuyang Li,Zhiqin Yang,Zhenyuan Zhang,Yunlong Lin,Sirui Han,Brandon Y. Feng.IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering[EB/OL].(2025-06-29)[2025-07-16].https://arxiv.org/abs/2506.23329.点此复制

评论