LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Novel View SynthesisImage CompressionSimilar Papers 제목 키워드 기반
LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
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 CloudsStreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
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 SynthesisGeneralizable Human Gaussian Splatting via Multi-view Semantic Consistency
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
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 EstimationG3Splat: Geometrically Consistent Generalizable Gaussian Splatting
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