Papers › NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven...

NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer

13 Mar 2023CVPR 2023 1arXiv:2303.06919archive 2025-07-28

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

Neural radiance fields (NeRF) show great success in novel view synthesis. However, in real-world scenes, recovering high-quality details from the source images is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation inaccuracy. Even with high-quality training frames, the synthetic novel views produced by NeRF models still suffer from notable rendering artifacts, such as noise, blur, etc. Towards to improve the synthesis quality of NeRF-based approaches, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm by learning a degradation-driven inter-viewpoint mixer. Specially, we design a NeRF-style degradation modeling approach and construct large-scale training data, enabling the possibility of effectively removing NeRF-native rendering artifacts for existing deep neural networks. Moreover, beyond the degradation removal, we propose an inter-viewpoint aggregation framework that is able to fuse highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

NeRFNeural RenderingNovel View Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Novel View Synthesis LLFF TensoRF + NeRFLiX LPIPS 0.149 #1 of 15 Archive leaderboard report
Novel View Synthesis LLFF TensoRF + NeRFLiX PSNR 27.39 #1 of 15 Archive leaderboard report
Novel View Synthesis LLFF TensoRF + NeRFLiX SSIM 0.867 #1 of 15 Archive leaderboard report
Novel View Synthesis LLFF Plenoxels + NeRFLiX LPIPS 0.156 #4 of 15 Archive leaderboard report
Novel View Synthesis LLFF Plenoxels + NeRFLiX PSNR 26.9 #4 of 15 Archive leaderboard report
Novel View Synthesis LLFF Plenoxels + NeRFLiX SSIM 0.864 #4 of 15 Archive leaderboard report
Novel View Synthesis Tanks and Temples TensoRF + NeRFLiX PSNR 28.94 #2 of 10 Archive leaderboard report
Novel View Synthesis Tanks and Temples TensoRF + NeRFLiX SSIM 0.93 #2 of 10 Archive leaderboard report
Novel View Synthesis Tanks and Temples Plenoxels + NeRFLiX PSNR 28.61 #3 of 10 Archive leaderboard report
Novel View Synthesis Tanks and Temples DIVeR + NeRFLiX SSIM 0.924 #10 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections