Contour Information Aware 2D Gaussian Splatting for Image Representation

TL;DR

This paper introduces a contour-aware 2D Gaussian Splatting method that incorporates segmentation priors to enhance edge preservation and reconstruction quality in image representation, especially under high compression.

Contribution

It proposes a novel framework that integrates object segmentation into Gaussian Splatting, preventing boundary blurring and improving edge fidelity in compressed image representations.

Findings

Improves edge preservation in Gaussian Splatting.

Achieves higher reconstruction quality with fewer Gaussians.

Maintains fast rendering and low memory usage.

Abstract

Image representation is a fundamental task in computer vision. Recently, Gaussian Splatting has emerged as an efficient representation framework, and its extension to 2D image representation enables lightweight, yet expressive modeling of visual content. While recent 2D Gaussian Splatting (2DGS) approaches provide compact storage and real-time decoding, they often produce blurry or indistinct boundaries when the number of Gaussians is small due to the lack of contour awareness. In this work, we propose a Contour Information-Aware 2D Gaussian Splatting framework that incorporates object segmentation priors into Gaussian-based image representation. By constraining each Gaussian to a specific segmentation region during rasterization, our method prevents cross-boundary blending and preserves edge structures under high compression. We also introduce a warm-up scheme to stabilize training and improve convergence. Experiments on synthetic color charts and the DAVIS dataset demonstrate that our approach achieves higher reconstruction quality around object edges compared to existing 2DGS methods. The improvement is particularly evident in scenarios with very few Gaussians, while our method still maintains fast rendering and low memory usage.