DANTE-W: Diffuse Albedo Neural Texturing in the Wild

2026-06-26

AI Summary

This work addresses the limitations of traditional mesh texturing methods, which directly fuse multi-view images and inadvertently bake lighting and shadows into the texture, thereby compromising visual fidelity under relighting. The authors propose a neural texture framework that recovers high-fidelity diffuse albedo from unstructured in-the-wild images and seamlessly integrates into standard 3D reconstruction pipelines. For the first time in large-scale outdoor scenes, this approach combines physics-based neural rendering with a generative albedo prior, leveraging neural texture representations, view-space priors, and surface parameterization to significantly enhance both textural detail and relighting consistency. Evaluated on a newly curated benchmark comprising both real-world and synthetic fine-grained textured scenes, the method demonstrates clear advantages in albedo reconstruction accuracy and relighting performance.

Abstract

Classical mesh texturing techniques blend captured multi-view images directly, which inevitably suffer from baked-in shading and casted shadows that compromise visual fidelity during relighting. To circumvent this issue, we present a neural texturing framework, namely DANTE-W, to enable high-fidelity diffuse albedo texture recovery from unstructured image collections for large-scale, in-the-wild scenes, which integrates seamlessly with traditional 3D reconstruction pipelines. Given a reconstructed mesh and its surface parameterization, our method fuses view-space generative albedo priors into a coherent texture space via an expressive neural representation, while substantially enhancing fine-grained textural details through physically principled neural rendering. To comprehensively evaluate our method, we curate a benchmark dataset featuring diverse, fine-grained textures, comprising both real-world in-the-wild scenes and synthetic objects. Extensive experiments verify the effectiveness of our approach in reconstructing accurate albedo textures and boosting relighting fidelity. Project page: dante-wild.github.io.

Problem

• diffuse albedo
• neural texturing
• in-the-wild scenes
• relighting fidelity
• mesh texturing

Innovation

• neural texturing
• diffuse albedo
• in-the-wild reconstruction
• physically-based rendering
• texture synthesis