AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer

Kun Zhou, Wenbo Li, Yi Wang, Tao Hu, Nianjuan Jiang, Xiaoguang Han, Jiangbo Lu

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 25 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
Apply NeRFLiX to NeRF-rendered viewsTensoRF, Plenoxels, NeRF-mm, NeRF, NLF, and RegNeRF · LLFF-P1 and LLFF-P2PSNR (dB): 26.73 -> 27.39; 26.29 -> 26.90; 22.98 -> 23.38; 26.50 -> 27.26; 27.46 -> 28.19; 19.10 -> 19.68; 23.06 -> 23.90; 24.81 ->Improved
Apply NeRFLiX to rendered viewsTensoRF and DIVeR · Tanks and TemplesPSNR (dB): 28.43 -> 28.94; 28.16 -> 28.61Improved
Apply NeRFLiX to rendered viewsTensoRF and Plenoxels · Noisy LLFF SyntheticPSNR (dB): 22.83 -> 24.12; 23.69 -> 25.51Improved
Apply NeRFLiX after shortened NeRF trainingTensoRF and Plenoxels · LLFF-P1PSNR (dB): 26.18 -> 27.14; 25.73 -> 26.60Improved
Use NDS instead of BSR-simulated degradation data (ablation)IVM · LLFF-P1PSNR (dB): 26.40 -> 27.39Improved
Add Re-Pos. degradation to SGN (ablation)NDS-trained model · LLFF-P1PSNR (dB): 27.08 -> 27.13Improved
Add A-Blur to SGN and Re-Pos. (ablation)NDS-trained model · LLFF-P1PSNR (dB): 27.13 -> 27.21Improved
Add region-adaptive degradation (ablation)NDS-trained model · LLFF-P1PSNR (dB): 27.21 -> 27.39Improved
Replace random reference selection with matching-cost view selection (ablation)IVM · LLFFPSNR (dB): 27.06dB -> 27.39dBImproved
Replace pixel-wise-only aggregation with hybrid recurrent aggregation (ablation)IVM · LLFF-P1PSNR (dB): 27.13 -> 27.39Improved
Replace patch-wise-only aggregation with hybrid recurrent aggregation (ablation)IVM · LLFF-P1PSNR (dB): 27.00 -> 27.39Improved
Increase hybrid aggregation from one to two iterations (ablation)IVM · LLFF-P1PSNR (dB): 27.21 -> 27.33Improved

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