AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields

Yue Chen, Xingyu Chen, Xuan Wang, Qi Zhang, Yu Guo, Ying Shan, Fei Wang

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 50 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
Replace direct global pose optimization with pixel-wise flexible alignment followed by a global geometric constraintNeRF on synthetic objects · Synthetic objects (mean)PSNR: 20.51 -> 28.62Improved
Replace direct global pose optimization with pixel-wise flexible alignment followed by a global geometric constraintNeRF on LLFF real-world scenes · Real-world scenes (LLFF mean)PSNR: 24.23 -> 24.54Improved
Use local-to-global registration instead of BARFNeural image alignment · Rigid perturbationsCorner error (pixels): 110.20 -> 0.31Improved
Use local-to-global registration instead of BARFNeural image alignment · Homography perturbationsCorner error (pixels): 30.21 -> 0.76Improved
Remove the global alignment loss (ablation)L2G-NeRF on synthetic objects · Synthetic objects (mean)PSNR: 22.70 -> 28.62Hurt
Remove the global alignment loss (ablation)L2G-NeRF on LLFF scenes · Real-world scenes (LLFF mean)PSNR: 20.71 -> 24.54Hurt
Increase the global alignment multiplier from 1 × 10² to 1 × 10³ (ablation)L2G-NeRF · FlowerPSNR: 24.59 -> 24.90Improved
Increase the global alignment multiplier from 1 × 10² to 1 × 10⁵ (ablation)L2G-NeRF · HornsPSNR: 22.51 -> 23.12Improved
Increase the global alignment multiplier (ablation)L2G-NeRF on Flower · FlowerconvergenceHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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