AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields

Xiangyu Wang, Jingsen Zhu, Qi Ye, Yuchi Huo, Yunlong Ran, Zhihua Zhong, Jiming Chen

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 19 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
split the single hash table into separate density and color grids (ablation)Instant-NGP backbone · NeRF Blender LegoPSNR: 34.44dB -> 35.08dB (training time 408s -> 441s)Improved
add local pretraining stage before global finetuning (ablation)Seal-3D student training · edited NeRF scenes (qualitative)edit completeness at 30 secondsImproved
add global finetuning after local pretraining (ablation)Seal-3D student training · edited NeRF scenes (qualitative)global qualityImproved
freeze MLP decoder parameters during local pretraining (ablation)Seal-3D pretraining stage · edited NeRF scenes (qualitative)global degenerationImproved
distill teacher edits into a student with multi-view trainingSeal-3D · edited NeRF scenes (qualitative)view-consistency artifactsImproved

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