paper-with-me

홈 › Papers

MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo

2024-05-20 · Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu

We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian representations and decode them into Gaussian parameters. 2) To further enhance performance, we propose a hybrid Gaussian rendering that integrates an efficient volume rendering design for novel view synthesis. 3) To support fast fine-tuning for specific scenes, we introduce a multi-view geometric consistent aggregation strategy to effectively aggregate the point clouds generated by the generalizable model, serving as the initialization for per-scene optimization. Compared with previous generalizable NeRF-based methods, which typically require minutes of fine-tuning and seconds of rendering per image, MVSGaussian achieves real-time rendering with better synthesis quality for each scene. Compared with the vanilla 3D-GS, MVSGaussian achieves better view synthesis with less training computational cost. Extensive experiments on DTU, Real Forward-facing, NeRF Synthetic, and Tanks and Temples datasets validate that MVSGaussian attains state-of-the-art performance with convincing generalizability, real-time rendering speed, and fast per-scene optimization.

📄 PDF Abstract BibTeX arXiv:2405.12218

Code (1)

TQTQliu/MVSGaussian 공식 구현 pytorch

Tasks

NeRFNovel View Synthesis

Similar Papers 제목 키워드 기반

SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting

2025-05-04 · Shubhendu Jena, Shishir Reddy Vutukur, Adnane Boukhayma

Recovering 3D information from scenes via multi-view stereo reconstruction (MVS) and novel view synthesis (NVS) is inherently challenging, particularly in scenarios involving sparse-view setups. The advent of 3D Gaussian…

3DGS3D Reconstruction3D Scene Reconstruction3D Shape Reconstruction+1

latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

2024-03-24 · Christopher Wewer, Kevin Raj, Eddy Ilg, Bernt Schiele 외

We present latentSplat, a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture. Existing methods for generalizable 3D reconstruction eith…

3D ReconstructionDecoder

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

Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting

2025-03-21 · CVPR 2025 1 · Jinbo Yan, Rui Peng, Zhiyan Wang, Luyang Tang 외

Building Free-Viewpoint Videos in a streaming manner offers the advantage of rapid responsiveness compared to offline training methods, greatly enhancing user experience. However, current streaming approaches face challe…

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