Rotated Lights for Consistent and Efficient 2D Gaussians Inverse Rendering

2026-02-09

AI Summary

This work addresses the challenges of albedo estimation bias and residual shading artifacts in inverse rendering caused by insufficient disentanglement between illumination and material properties. To this end, we propose an efficient inverse rendering framework that integrates a rotating light acquisition strategy (RotLight) with a proxy mesh representation. By leveraging only a few object rotations, our method enables accurate incident light tracking, while the proxy mesh introduces residual constraints and facilitates global illumination optimization. This approach significantly enhances the accuracy of material–illumination decomposition within the 2D Gaussian splatting representation. Experiments on both synthetic and real-world datasets demonstrate that our method markedly reduces visual artifacts, improves albedo estimation quality, and maintains computational efficiency.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Responsible Web: Algorithmic accountability and transparency on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Inverse rendering aims to decompose a scene into its geometry, material properties and light conditions under a certain rendering model. It has wide applications like view synthesis, relighting, and scene editing. In recent years, inverse rendering methods have been inspired by view synthesis approaches like neural radiance fields and Gaussian splatting, which are capable of efficiently decomposing a scene into its geometry and radiance. They then further estimate the material and lighting that lead to the observed scene radiance. However, the latter step is highly ambiguous and prior works suffer from inaccurate color and baked shadows in their albedo estimation albeit their regularization. To this end, we propose RotLight, a simple capturing setup, to address the ambiguity. Compared to a usual capture, RotLight only requires the object to be rotated several times during the process. We show that as few as two rotations is effective in reducing artifacts. To further improve 2DGS-based inverse rendering, we additionally introduce a proxy mesh that not only allows accurate incident light tracing, but also enables a residual constraint and improves global illumination handling. We demonstrate with both synthetic and real world datasets that our method achieves superior albedo estimation while keeping efficient computation.

Problem

• inverse rendering
• albedo estimation
• lighting decomposition
• 2D Gaussian splatting
• scene decomposition

Innovation

• Rotated Lights
• Inverse Rendering
• 2D Gaussian Splatting
• Albedo Estimation
• Proxy Mesh