SyncAI.news, a Varaisys broadcasting
Beyond Appearance: Evidence-Guided Programmatic 3D Scene Reconstruction with Agentic Lighting Reasoning
ZL

Zeting Luo, Yifan Li, Shuai Yang

· 1 min read

ResearcharXiv cs.CV

Beyond Appearance: Evidence-Guided Programmatic 3D Scene Reconstruction with Agentic Lighting Reasoning

arXiv:2611.24565v1 Announce Type: new Abstract: Image-to-code methods for 3D scene reconstruction produce executable code that generates editable digital content and supports visual simulation. However, existing methods primarily rely on appearance similarity, which provides limited guidance for distinguishing errors in geometry, materials, and illumination. Light shapes scene appearance through its interactions with geometry and materials, influencing shading, cast shadows, and reflections. We therefore present LightHarness, a VLM-based agentic framework that incorporates explicit lighting reasoning into iterative scene reconstruction. To be specific, we leverage complementary geometric, intrinsic, and illumination cues to jointly refine scene structure and appearance, and propose Lighting Reasoning Memory to maintain light-source hypotheses, which supports evidence, and revision history throughout iterations. Together, they support reasoning about partially visible and unseen sources, with evidence-guided verification directing subsequent revisions. Our framework reconstructs explicit scenes through coherent reasoning about geometry, materials, and illumination without additional training or differentiable rendering. Extensive experiments demonstrate superior image-to-code reconstruction accuracy under challenging shadows and complex illumination, further supporting downstream scene editing, object insertion, and versatile relighting.

Original source

This story was published by arXiv cs.CV and written by Zeting Luo, Yifan Li, Shuai Yang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News