paper-with-me

홈 › Papers

LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images

2025-07-22 · Guichen Huang, Ruoyu Wang, Xiangjun Gao, Che Sun, Yuwei Wu, Shenghua Gao, Yunde Jia arxiv

3D Gaussian Splatting achieves high-fidelity novel view synthesis, but its application to online long-sequence scenarios is still limited. Existing methods either rely on slow per-scene optimization or fail to provide efficient incremental updates, hindering continuous performance. In this paper, we propose LongSplat, an online real-time 3D Gaussian reconstruction framework designed for long-sequence image input. The core idea is a streaming update mechanism that incrementally integrates current-view observations while selectively compressing redundant historical Gaussians. Crucial to this mechanism is our Gaussian-Image Representation (GIR), a representation that encodes 3D Gaussian parameters into a structured, image-like 2D format. GIR simultaneously enables efficient fusion of current-view and historical Gaussians and identity-aware redundancy compression. These functions enable online reconstruction and adapt the model to long sequences without overwhelming memory or computational costs. Furthermore, we leverage an existing image compression method to guide the generation of more compact and higher-quality 3D Gaussians. Extensive evaluations demonstrate that LongSplat achieves state-of-the-art efficiency-quality trade-offs in real-time novel view synthesis, delivering real-time reconstruction while reducing Gaussian counts by 44\% compared to existing per-pixel Gaussian prediction methods.

📄 PDF Abstract BibTeX arXiv:2507.16144

Code (0)

등록된 구현이 없습니다.

Tasks

Novel View SynthesisImage Compression

Similar Papers 제목 키워드 기반

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

2025-08-19 · Chin-Yang Lin, Cheng Sun, Fu-En Yang, Min-Hung Chen 외 arxiv

LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer …

Computational EfficiencyNovel View SynthesisPose EstimationPoint Clouds

StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams

2025-03-08 · Yang Li, Jinglu Wang, Lei Chu, Xiao Li 외

The advent of 3D Gaussian Splatting (3DGS) has advanced 3D scene reconstruction and novel view synthesis. With the growing interest of interactive applications that need immediate feedback, online 3DGS reconstruction in …

3DGS3D Scene ReconstructionNovel View Synthesis

Generalizable Human Gaussian Splatting via Multi-view Semantic Consistency

2026-04-28 · Jingi Kim, Wonjun Kim arxiv

Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined struct…

HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features

2024-11-05 · Arnab Dey, Cheng-You Lu, Andrew I. Comport, Srinath Sridhar 외

Recent advancements in radiance field rendering show promising results in 3D scene representation, where Gaussian splatting-based techniques emerge as state-of-the-art due to their quality and efficiency. Gaussian splatt…

Feature SplattingPose Estimation

G3Splat: Geometrically Consistent Generalizable Gaussian Splatting

2025-12-19 · Mehdi Hosseinzadeh, Shin-Fang Chng, Yi Xu, Simon Lucey 외 arxiv

3D Gaussians have become a powerful scene representation for real-time splatting and high-quality novel-view synthesis. This has motivated generalizable splatting -- methods that adapt feed-forward geometry prediction ne…

Pose Estimation