SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination

2026-09-09

AI Summary

SceneHI通过将2D扩散模型的高分辨率光照感知先验提升到3D纹理合成，解决了在3D对象上直接生成高质量纹理的问题，无需微调或优化模型。

Abstract

SceneHI is a framework that lifts high-resolution, illumination-aware priors from 2D diffusion models to perform 3D texture synthesis. It is the first to demonstrate that high-resolution textures, previously limited to 2D synthesis, can be generated directly on 3D objects without model fine-tuning or optimization. Designed for complex, multi-object environments, SceneHI uniquely combines 3D-consistency, high-resolution fidelity, and physically plausible baked shadows within a single generative pipeline. To enforce strict geometric coherence, we introduce an exact analytical pixel-to-texel mapping that aligns diffusion trajectories across multiple viewpoints. We utilize High-Resolution Latent Textures (HRLTs) as a persistent canvas for gradually denoised textures, while camera views perform the denoising steps in latent pixel space. This ensures a shared base texture that can be subsequently refined to high resolution without compromising multi-view consistency. Finally, a light-aware generative pass embeds realistic geometry-consistent shadows directly into the atlases, bridging the gap to production workflows. SceneHI achieves high visual fidelity while reducing generation time by 80% compared to existing scene-level methods.

Problem

• high-resolution
• illumination-aware
• 3D texture synthesis
• multi-view consistency
• geometric coherence

Innovation

• High-Resolution Textures
• 3D-Consistency
• Illumination-aware Priors
• Pixel-to-Texel Mapping
• HRLTs