See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization

TL;DR

This paper introduces a novel sparse-view 3D Gaussian Splatting method that incorporates semantic and depth regularization to improve rendering quality and detail preservation in novel view synthesis.

Contribution

It proposes a new regularization approach using semantic features from DINO-ViT and local depth constraints to enhance sparse-view 3D Gaussian Splatting performance.

Findings

Achieves up to 0.4dB PSNR improvement on LLFF dataset.

Reduces distortion and enhances visual quality in sparse-view synthesis.

Outperforms existing state-of-the-art methods.

Abstract

3D Gaussian Splatting (3DGS) has shown remarkable performance in novel view synthesis. However, its rendering quality deteriorates with sparse inphut views, leading to distorted content and reduced details. This limitation hinders its practical application. To address this issue, we propose a sparse-view 3DGS method. Given the inherently ill-posed nature of sparse-view rendering, incorporating prior information is crucial. We propose a semantic regularization technique, using features extracted from the pretrained DINO-ViT model, to ensure multi-view semantic consistency. Additionally, we propose local depth regularization, which constrains depth values to improve generalization on unseen views. Our method outperforms state-of-the-art novel view synthesis approaches, achieving up to 0.4dB improvement in terms of PSNR on the LLFF dataset, with reduced distortion and enhanced visual quality.