cs.CVNov 18, 2026

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

Authors: Zeting Luo, Yifan Li, Shuai Yang

Organizations: Wangxuan Institute of Computer Technology, Peking University

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.

Figures & tables

Explore similar work

CardsList
  1. LEGO-Anything: Coding Agents for 3D Scene Reconstruction

    Sep 28, 2026Xirui Li, Peng Shi, Mingwen Dong +73D ReconstructionCoding Agents

  2. Engine-Native Editable 3D World Reconstruction with Objects and Lighting

    Jul 23, 2026Junhao Chen, Xinghao Chen, Henghaofan Zhang +83D Reconstruction3D Object Detection

  3. SceneAnything: Agentic Reconstruction of Large-Scale Mesh Scenes from a Single Video

    Nov 19, 2026Bowen Xue, Saeed Hadadan, Fabrice Rousselle +33D Reconstruction3D Mesh Reconstruction