Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting

TL;DR

This paper introduces Gaussian-DK, a method that improves real-time view synthesis from dark, inconsistent images by modeling a consistent radiance field with anisotropic 3D Gaussians and compensating for camera response variations.

Contribution

We propose Gaussian-DK, a novel approach that addresses multi-view inconsistency in dark environments by modeling physical radiance and correcting camera response effects.

Findings

Gaussian-DK outperforms existing methods on our benchmark dataset.

It produces high-quality renderings without ghosting or floaters.

The method enables synthesis of illuminated images showing shadow details.

Abstract

3D Gaussian Splatting has recently emerged as a powerful representation that can synthesize remarkable novel views using consistent multi-view images as input. However, we notice that images captured in dark environments where the scenes are not fully illuminated can exhibit considerable brightness variations and multi-view inconsistency, which poses great challenges to 3D Gaussian Splatting and severely degrades its performance. To tackle this problem, we propose Gaussian-DK. Observing that inconsistencies are mainly caused by camera imaging, we represent a consistent radiance field of the physical world using a set of anisotropic 3D Gaussians, and design a camera response module to compensate for multi-view inconsistencies. We also introduce a step-based gradient scaling strategy to constrain Gaussians near the camera, which turn out to be floaters, from splitting and cloning. Experiments on our proposed benchmark dataset demonstrate that Gaussian-DK produces high-quality renderings without ghosting and floater artifacts and significantly outperforms existing methods. Furthermore, we can also synthesize light-up images by controlling exposure levels that clearly show details in shadow areas.