GSsplat: Generalizable Semantic Gaussian Splatting for Novel-view Synthesis in 3D Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Feng, Xu, Hongbin, Liang, Wanlin, Kang, Wenxiong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915277348798464
author Xiao, Feng
Xu, Hongbin
Liang, Wanlin
Kang, Wenxiong
author_facet Xiao, Feng
Xu, Hongbin
Liang, Wanlin
Kang, Wenxiong
contents The semantic synthesis of unseen scenes from multiple viewpoints is crucial for research in 3D scene understanding. Current methods are capable of rendering novel-view images and semantic maps by reconstructing generalizable Neural Radiance Fields. However, they often suffer from limitations in speed and segmentation performance. We propose a generalizable semantic Gaussian Splatting method (GSsplat) for efficient novel-view synthesis. Our model predicts the positions and attributes of scene-adaptive Gaussian distributions from once input, replacing the densification and pruning processes of traditional scene-specific Gaussian Splatting. In the multi-task framework, a hybrid network is designed to extract color and semantic information and predict Gaussian parameters. To augment the spatial perception of Gaussians for high-quality rendering, we put forward a novel offset learning module through group-based supervision and a point-level interaction module with spatial unit aggregation. When evaluated with varying numbers of multi-view inputs, GSsplat achieves state-of-the-art performance for semantic synthesis at the fastest speed.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04659
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GSsplat: Generalizable Semantic Gaussian Splatting for Novel-view Synthesis in 3D Scenes
Xiao, Feng
Xu, Hongbin
Liang, Wanlin
Kang, Wenxiong
Graphics
The semantic synthesis of unseen scenes from multiple viewpoints is crucial for research in 3D scene understanding. Current methods are capable of rendering novel-view images and semantic maps by reconstructing generalizable Neural Radiance Fields. However, they often suffer from limitations in speed and segmentation performance. We propose a generalizable semantic Gaussian Splatting method (GSsplat) for efficient novel-view synthesis. Our model predicts the positions and attributes of scene-adaptive Gaussian distributions from once input, replacing the densification and pruning processes of traditional scene-specific Gaussian Splatting. In the multi-task framework, a hybrid network is designed to extract color and semantic information and predict Gaussian parameters. To augment the spatial perception of Gaussians for high-quality rendering, we put forward a novel offset learning module through group-based supervision and a point-level interaction module with spatial unit aggregation. When evaluated with varying numbers of multi-view inputs, GSsplat achieves state-of-the-art performance for semantic synthesis at the fastest speed.
title GSsplat: Generalizable Semantic Gaussian Splatting for Novel-view Synthesis in 3D Scenes
topic Graphics
url https://arxiv.org/abs/2505.04659