LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yilong, Li, Wanhua, Zhu-Tian, Chen, Pfister, Hanspeter
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914591078875136
author Liu, Yilong
Li, Wanhua
Zhu-Tian, Chen
Pfister, Hanspeter
author_facet Liu, Yilong
Li, Wanhua
Zhu-Tian, Chen
Pfister, Hanspeter
contents We present LangFlash, a feed-forward framework for 3D Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enriched with language-aligned semantic features from sparse unposed multi-view images. Unlike optimization-based 3D methods, LangFlash directly predicts the geometry and semantics in a single forward pass, enabling low-latency 3D reconstruction and language-consistent scene understanding. To support large-scale training, we enriched the RealEstate10k dataset with coherent and dense semantic information for 3D semantic supervision. Furthermore, we propose a sparse semantic encoding scheme that combines a global semantic dictionary with locally varying per-primitive weights, preserving high-level linguistic information, while reducing representation complexity. Experimental results show that LangFlash achieves superior novel view synthesis and semantic consistency compared with previous methods. This study establishes a new paradigm for pose-free, language-grounded 3D scene reconstruction, advancing generalizable 3D vision and multimodal scene understanding. Demo is available at https://liylo.github.io/langflash.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23287
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images
Liu, Yilong
Li, Wanhua
Zhu-Tian, Chen
Pfister, Hanspeter
Computer Vision and Pattern Recognition
We present LangFlash, a feed-forward framework for 3D Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enriched with language-aligned semantic features from sparse unposed multi-view images. Unlike optimization-based 3D methods, LangFlash directly predicts the geometry and semantics in a single forward pass, enabling low-latency 3D reconstruction and language-consistent scene understanding. To support large-scale training, we enriched the RealEstate10k dataset with coherent and dense semantic information for 3D semantic supervision. Furthermore, we propose a sparse semantic encoding scheme that combines a global semantic dictionary with locally varying per-primitive weights, preserving high-level linguistic information, while reducing representation complexity. Experimental results show that LangFlash achieves superior novel view synthesis and semantic consistency compared with previous methods. This study establishes a new paradigm for pose-free, language-grounded 3D scene reconstruction, advancing generalizable 3D vision and multimodal scene understanding. Demo is available at https://liylo.github.io/langflash.github.io/.
title LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.23287