Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis

2026-02-20

AI Summary

This work addresses photometric and chromatic inconsistencies across multi-view images—caused by variations in lighting, sensor response, and ISP configurations—that violate the photometric consistency assumption in novel view synthesis and degrade reconstruction and rendering quality. Within the 3D Gaussian Splatting (3DGS) framework, the authors propose a unified color correction method that requires no modification to the explicit 3D representation. The approach integrates global viewpoint-adaptive brightness adjustment with local pixel-level residual refinement, jointly optimizing brightness correction, geometry, and photometric consistency under an unsupervised multi-view consistency constraint. To the best of our knowledge, this is the first method in 3DGS to simultaneously handle both brightness and color correction, significantly improving reconstruction fidelity and rendering robustness under challenging illumination conditions such as low light or overexposure, while preserving real-time performance.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

High-quality image acquisition in real-world environments remains challenging due to complex illumination variations and inherent limitations of camera imaging pipelines. These issues are exacerbated in multi-view capture, where differences in lighting, sensor responses, and image signal processor (ISP) configurations introduce photometric and chromatic inconsistencies that violate the assumptions of photometric consistency underlying modern 3D novel view synthesis (NVS) methods, including Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), leading to degraded reconstruction and rendering quality. We propose Luminance-GS++, a 3DGS-based framework for robust NVS under diverse illumination conditions. Our method combines a globally view-adaptive lightness adjustment with a local pixel-wise residual refinement for precise color correction. We further design unsupervised objectives that jointly enforce lightness correction and multi-view geometric and photometric consistency. Extensive experiments demonstrate state-of-the-art performance across challenging scenarios, including low-light, overexposure, and complex luminance and chromatic variations. Unlike prior approaches that modify the underlying representation, our method preserves the explicit 3DGS formulation, improving reconstruction fidelity while maintaining real-time rendering efficiency.

Problem

• photometric inconsistency
• chromatic inconsistency
• novel view synthesis
• illumination variation
• multi-view capture

Innovation

• view-adaptive curve adjustment
• lightness correction
• color correction
• 3D Gaussian Splatting
• photometric consistency