AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Multi-view Pyramid Transformer: Look Coarser to See Broader

Gyeongjin Kang, Seungkwon Yang, Seungtae Nam, Younggeun Lee, Jungwoo Kim, Eunbyung Park

CVPR 2026 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 5 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 pyramidal feature aggregation from all stages (ablation)MVP · DL3DV (256x256 ablation)PSNR: 21.58 -> 22.79Improved
use forward fine-to-coarse hierarchy instead of reversed hierarchy (ablation)MVP · DL3DV (256x256 ablation)PSNR: 18.95 -> 22.79Improved
use group-wise attention instead of frame-wise attention in stage 2 (ablation)MVP · DL3DV (256x256 ablation)PSNR: 22.53 -> 22.79Improved
use global attention instead of group-wise attention in stage 2 (ablation)MVP · DL3DV (256x256 ablation)PSNR: 22.79 -> 22.94Mixed
add inter-view hierarchy (local-to-global attention) (ablation)MVP · DL3DV (256x256 ablation)PSNR: 22.94 -> 22.79Mixed
add intra-view token merging hierarchy (ablation)MVP · DL3DV (256x256 ablation)LPIPS: 0.249 -> 0.235Improved
add register tokens (ablation)MVP · DL3DV (256x256 ablation)PSNR: 22.52 -> 22.79Improved
use group size 4 instead of group size 2 (ablation)MVP · DL3DV (256x256 ablation)PSNR: 22.94 -> 23.18Improved
use group size 8 instead of group size 4 (ablation)MVP · DL3DV (256x256 ablation)PSNR: 23.18 -> 23.18No clear effect
use fine patch sizes (4, 8, 16) instead of coarse (8, 16, 32) (ablation)MVP · RE10K (4 views, 256x256)PSNR: 30.56 -> 32.12Improved
prune Gaussians with opacity below 0.01 at render timeMVP · DL3DVPSNR: -0.02 to -0.15 PSNR with 79.7% to 89.1% prunedNo clear effect

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