AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization

Yuechen Zhang, Zexin He, Jinbo Xing, Xufeng Yao, Jiaya Jia

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 32 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
Use reference-based ray registration and template-based semantic correspondenceRef-NPR · Novel-view stylizationRef-LPIPS: 0.394 -> 0.339Improved
Use reference-based ray registration and template-based semantic correspondenceRef-NPR · Novel-view stylizationRobustness: 26.34 -> 28.11Improved
Use Ref-NPR rather than ARFStylization user study · Stylization sequencesAverage rank: 2.52 -> 1.73Improved
Remove pseudo-ray supervision (reference loss) (ablation)Ref-NPR · Stylized novel viewsVisual qualityHurt
Use reference-view rays only instead of registered pseudo-rays (ablation)Ref-NPR · Stylized novel viewsTexture detailHurt
Remove semantic feature supervision (ablation)Ref-NPR · Occluded regionsSemantic stylizationHurt
Remove coarse color-matching supervision (ablation)Ref-NPR · Occluded regionsColor consistencyHurt
Remove Template-based Correspondence Module (ablation)Ref-NPR · Occluded regionsSemantic correspondenceHurt
Remove smooth content update strategy (ablation)Ref-NPR · Occluded regionsStylization qualityHurt
Use Texler rather than Ref-NPRNovel-view stylization · Reference-related novel viewsRef-LPIPS: 0.339 -> 0.335Improved

Later papers that compared with this method

6 later accepted papers report Ref-NPR as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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