Papers
arxiv:2506.10335

PointGS: Point Attention-Aware Sparse View Synthesis with Gaussian Splatting

Published on Jun 12
Authors:
,
,
,
,

Abstract

A Point-wise Feature-Aware Gaussian Splatting framework enhances real-time rendering quality from sparse views using stereo models, dense point clouds, and self-attention mechanisms.

AI-generated summary

3D Gaussian splatting (3DGS) is an innovative rendering technique that surpasses the neural radiance field (NeRF) in both rendering speed and visual quality by leveraging an explicit 3D scene representation. Existing 3DGS approaches require a large number of calibrated views to generate a consistent and complete scene representation. When input views are limited, 3DGS tends to overfit the training views, leading to noticeable degradation in rendering quality. To address this limitation, we propose a Point-wise Feature-Aware Gaussian Splatting framework that enables real-time, high-quality rendering from sparse training views. Specifically, we first employ the latest stereo foundation model to estimate accurate camera poses and reconstruct a dense point cloud for Gaussian initialization. We then encode the colour attributes of each 3D Gaussian by sampling and aggregating multiscale 2D appearance features from sparse inputs. To enhance point-wise appearance representation, we design a point interaction network based on a self-attention mechanism, allowing each Gaussian point to interact with its nearest neighbors. These enriched features are subsequently decoded into Gaussian parameters through two lightweight multi-layer perceptrons (MLPs) for final rendering. Extensive experiments on diverse benchmarks demonstrate that our method significantly outperforms NeRF-based approaches and achieves competitive performance under few-shot settings compared to the state-of-the-art 3DGS methods.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.10335 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.10335 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.10335 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.