AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene

Wenjie Mu, Zhan Li, Chuanzhou Su, Xuanyi Shen, Ziniu Liu, Fan Lu, Yujian Mo, Junqiao Zhao, Tiantian Feng, Chen Ye, Guang Chen

CVPR 2026 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 0 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 MU-GeNeRF instead of ReTR without per-scene optimizationgeneralizable NeRF · On-the-go CornerPSNR: 16.33 -> 17.96Improved
use MU-GeNeRF instead of ReTR without per-scene optimizationgeneralizable NeRF · On-the-go PatioPSNR: 16.39 -> 18.63Improved
use MU-GeNeRF instead of MuRF without per-scene optimizationgeneralizable NeRF · RobustNeRF StatuePSNR: 12.88 -> 18.28Improved
use MU-GeNeRF instead of ReTR without per-scene optimizationgeneralizable NeRF · RobustNeRF AndroidPSNR: 18.63 -> 19.87Improved
add per-scene fine-tuning to MU-GeNeRFMU-GeNeRF · On-the-go CornerPSNR: 17.96 -> 21.77Improved
add per-scene fine-tuning to MU-GeNeRFMU-GeNeRF · RobustNeRF AndroidPSNR: 19.87 -> 22.34Improved
use MU-GeNeRF ft instead of ReTR ftfine-tuned generalizable NeRF · On-the-go PatioPSNR: 17.97 -> 20.72Improved
use MU-GeNeRF ft instead of UP-NeRFfine-tuned methods · On-the-go PatioPSNR: 15.78 -> 20.72Improved
use scene-specific NeRF on-the-go instead of MU-GeNeRF ftfine-tuned methods · On-the-go CornerPSNR: 23.15 vs 21.77Hurt
use scene-specific NeRF on-the-go instead of MU-GeNeRF ftfine-tuned methods · RobustNeRF StatuePSNR: 21.25 vs 19.97Hurt
use MU-GeNeRF instead of ReTR without per-scene optimizationgeneralizable NeRF · On-the-go Patio-HighLPIPS: 0.593 -> 0.507Improved
use released pretrained MuRF weights instead of training from scratch, then fine-tuneMuRF ft · On-the-go CornerPSNR: 13.57 -> 14.03No clear effect

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