AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

NeRF-MS: Neural Radiance Fields with Multi-Sequence

Peihao Li, Shaohui Wang, Chen Yang, Bingbing Liu, Weichao Qiu, Haoqian Wang

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 14 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 triplet loss to regularize per-image appearance codes (ablation)NeRF-MS · NeRF-OSRPSNR: 20.848 -> 21.611Improved
add triplet loss to regularize appearance codes (ablation)NeRF-MS · NeRF-OSRLPIPS: 0.3410 -> 0.3167Improved
use per-image appearance code with triplet loss instead of per-sequence appearance code (ablation)NeRF-MS · NeRF-OSRPSNR: 20.366 -> 21.611Improved
add sequence transient code to transient decomposition (ablation)NeRF-MS · NeRF-OSRPSNR: 21.224 -> 21.611Improved
add sequence transient code (ablation)NeRF-MS · NeRF-OSRSSIM: 0.6846 -> 0.7160Improved
per-sequence appearance code vs no triplet loss per-image code (ablation)NeRF-MS · NeRF-OSRLPIPS: 0.3410 -> 0.3645Hurt
introduce sequence label error (merge two sequences) (ablation)NeRF-MS · NeRF-OSR stjohannPSNR: 22.839 -> 21.668Hurt
use NeRF-MS instead of NeRF-W in NeRF-W-like setting (50 sequences, 2 images each)synthetic NeRF dataset · NeRF Synthetic multi-sequenceimage qualityImproved

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