Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment
This addresses photometric inconsistencies in multi-view scenarios for applications like photography and computer vision, but it is incremental as it adapts an existing method (3D Gaussian Splatting) without altering its core representation.
The paper tackled novel view synthesis under challenging lighting conditions like low-light and overexposure by introducing Luminance-GS, which achieved state-of-the-art results with real-time rendering speed and improved reconstruction quality compared to previous baselines.
Capturing high-quality photographs under diverse real-world lighting conditions is challenging, as both natural lighting (e.g., low-light) and camera exposure settings (e.g., exposure time) significantly impact image quality. This challenge becomes more pronounced in multi-view scenarios, where variations in lighting and image signal processor (ISP) settings across viewpoints introduce photometric inconsistencies. Such lighting degradations and view-dependent variations pose substantial challenges to novel view synthesis (NVS) frameworks based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). To address this, we introduce Luminance-GS, a novel approach to achieving high-quality novel view synthesis results under diverse challenging lighting conditions using 3DGS. By adopting per-view color matrix mapping and view-adaptive curve adjustments, Luminance-GS achieves state-of-the-art (SOTA) results across various lighting conditions -- including low-light, overexposure, and varying exposure -- while not altering the original 3DGS explicit representation. Compared to previous NeRF- and 3DGS-based baselines, Luminance-GS provides real-time rendering speed with improved reconstruction quality.