AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GaussReg: Fast 3D Registration with Gaussian Splatting

Jiahao Chang, Yinglin Xu, Yihao Li, Yuantao Chen, Wensen Feng, Xiaoguang Han

ECCV 2024 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 21 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add image-guided fine registration after coarse registration (ablation)GaussReg · ScanNet-GSRegRTE: 0.061 -> 0.042Improved
add image-guided fine registration on real-world scenes (ablation)GaussReg · GSRegRRE: 6.904 -> 2.989Improved
use HLoc instead of learned fine registration after coarse alignment (ablation)GaussReg · ScanNet-GSRegsuccess ratio: 1.000 -> 0.512Hurt
GS registration vs HLoc image matching (SfM) baselineGaussReg · ScanNet-GSRegtime (s): 212.3 -> 4.8Improved
use point cloud registration baselines on noisy GS point cloudsFGR, REGTR · ScanNet-GSRegRRE: 157.126 (FGR), 80.095 (REGTR) vs 2.827Hurt
increase top-k camera pairs from 5 to 10 (ablation)overlap image selection · ScanNet-GSRegRTE: 0.115 -> 0.042Improved
increase top-k beyond 10 (ablation)overlap image selection · ScanNet-GSRegRTE: 0.042 -> 0.063 (k=20)No clear effect
add image-guided 3D (I3D) feature extraction instead of MVSNet depth projection (ablation)GaussReg fine registration · ScanNet-GSRegRSE: RRE 3.169 -> 2.827, RSE 0.061 -> 0.032, RTE 0.036 -> 0.042, RDE 0.066 -> 0.080Mixed
apply coarse registration alone to object-level registrationGaussReg coarse · ObjaverseRRE: 9.67 -> 2.47Improved

Later papers that compared with this method

2 later accepted papers report GaussReg as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy