AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

OPONeRF: One-Point-One NeRF for Robust Few-shot Rendering

Yu Zheng, Yueqi Duan, Kangfu Zheng, Hongru Yan, Jiwen Lu, Jie Zhou

IJCV 2025 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 3 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
add adaptiveness factor (ablation)OPONeRF · Cut Roasted BeefPSNR: 29.32 -> 31.76Improved
add probabilistic modeling (ablation)OPONeRF · Cut Roasted BeefPSNR: 30.26 -> 31.76Improved
add probabilistic modeling (ablation)OPONeRF · Kubric scene WPSNR: 34.13 -> 35.23Improved
use interpolation then regression for adaptiveness factor instead of direct regression (ablation)OPONeRF · Cut Roasted BeefPSNR: 29.51 -> 31.76Improved
use learned adaptiveness factor instead of all-ones (ablation)OPONeRF · Cut Roasted BeefPSNR: 28.93 -> 31.76Improved
use learned binary weight mask instead of all-zeros (ablation)OPONeRF · Cut Roasted BeefPSNR: 24.05 -> 31.76Improved
add quantization in PCD module (ablation)OPONeRF · Cut Roasted BeefPSNR: 24.20 -> 31.76Improved
add diversity loss (ablation)OPONeRF · Kubric scene WPSNR: 34.43 -> 35.23Improved
add residual connection in point representation (ablation)OPONeRF · Cut Roasted BeefPSNR: 26.41 -> 31.76Improved
add deterministic invariance term (ablation)OPONeRF · Cut Roasted BeefPSNR: 27.00 -> 31.76Improved
incorporate OPONeRF into MVSNeRFMVSNeRF · Sear SteakPSNR: 23.87 -> 25.13Improved
incorporate OPONeRF into NeuRayNeuRay · VR HeadsetPSNR: 28.61 -> 29.35Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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