AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

RS-NeRF: Neural Radiance Fields from Rolling Shutter Images

Muyao Niu, Tong Chen, Yifan Zhan, Zhuoxiao Li, Xiang Ji, Yinqiang Zheng

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 6 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 trajectory smoothness regularization to vanilla RS-NeRF (ablation)Vanilla RS-NeRF · Synthetic scenes, on-trajectoryPSNR: 21.47 -> 24.06Improved
add multi-sampling to vanilla RS-NeRF (ablation)Vanilla RS-NeRF · Synthetic scenes, on-trajectoryPSNR: 21.47 -> 24.89Improved
add multi-sampling and smoothness regularization together (ablation)Vanilla RS-NeRF · Synthetic scenes, out-of-trajectoryPSNR: 21.68 -> 28.65Improved
add smoothness regularization to improve camera trajectory estimate (ablation)Vanilla RS-NeRF · Synthetic scenesMSTE: 0.0509 -> 0.0358Improved
add multi-sampling to improve camera trajectory estimate (ablation)Vanilla RS-NeRF · Synthetic scenesMSTE: 0.0509 -> 0.0462Improved
use 100 poses per frame instead of 400 (ablation)Vanilla RS-NeRF · Synthetic scenes, on-trajectoryPSNR: 24.06 -> 24.36Improved
perturb initial poses with random SE(3) noise (ablation)RS-NeRF · Synthetic scenes, on-trajectoryPSNR: 27.93 -> 28.47 (U[-0.05, 0.05])No clear effect
use RS-NeRF versus two-stage 2D correction then NeRFnovel view synthesis from RS images · Synthetic scenes, out-of-trajectoryPSNR: 22.18 -> 28.65 (JAMNet+NeRF vs RS-NeRF)Improved
use RS-NeRF versus USB-NeRF, which models per-row poses without improvementsnovel view synthesis from RS images · Synthetic scenes, on-trajectoryPSNR: 25.02 -> 27.93Improved

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