AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

MS-NeRF: Multi-Space Neural Radiance Fields

Ze-Xin Yin, Pengyi Jiao, Jiaxiong Qiu, Ming‐Ming Cheng, Bo Ren

TPAMI 2025 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 9 citations (OpenAlex)

Read the paper

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 neural feature fields in place of direct RGB-G outputs (ablation)MS-Mip-NeRF 360 · Synthetic mirror datasetPSNR: 37.50 -> 38.84Improved
use the MLP-based feature-field module instead of the hybrid module (ablation)MS-Mip-NeRF 360 · Synthetic mirror datasetPSNR: 33.59 -> 38.84Improved
gate from positional-encoding MLP instead of grid features (ablation)MS-TensoRF · Synthetic mirror dataset, 10 scenesPSNR: 32.07 -> 34.72Improved
add the MS moduleMip-NeRF 360 · Synthetic mirror dataset, circle path, reflective areasPSNR: 24.20 -> 28.35Improved
add the MS moduleMip-NeRF 360 · Synthetic mirror dataset, circle path, other areasPSNR: 37.06 -> 37.65No clear effect
add the MS moduleMip-NeRF · Realistic Synthetic 360PSNR: 30.74 -> 30.81No clear effect
add the MS moduleMip-NeRF · Real Forward-FacingPSNR: 25.78 -> 25.59No clear effect
add the MS module with only 30 input views, mirror-passing path (ablation)Mip-NeRF 360 · Scene01-05 mirror-passing-through pathPSNR: 21.60 -> 21.58 (reflective), 25.11 -> 23.04 (other)Mixed
add the MS module with 30 input views, circle path (ablation)Mip-NeRF 360 · Scene01-05 circle pathPSNR: 19.08 -> 28.37Improved
use feature fields instead of radiance fields in iNGP (ablation)iNGP · Realistic Synthetic 360PSNR: 33.43 -> 33.25Hurt
add the MS module to NeuSNeuS · Synthetic mirror dataset, circle pathPSNR: 25.86 -> 28.65Improved
use MSE loss instead of MAE loss (ablation)MS-NeRF_B · Scene01-05 circle pathPSNR: 24.31 -> 28.09Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 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