AI Paper Atlas

Research map / 3D vision / Depth and stereo

Long-Range Grouping Transformer for Multi-View 3D Reconstruction

Liying Yang, Zhenwei Zhu, Xuxin Lin, Jian Nong, Yanyan Liang

ICCV 2023 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 26 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 long-range grouping attention for inter-view communication instead of per-view-only self-attention (ablation)LRGT encoder · ShapeNet 20 viewsIoU: 0.7682 -> 0.7742 (LGA without IFS)Improved
add inter-view feature signatures (IFS) on top of LGA (ablation)LRGT encoder · ShapeNet 20 viewsIoU: 0.7742 -> 0.7786Improved
add skip connection combining deconvolution and transformer features in HR basic unit (ablation)LRGT decoder · ShapeNet 3 viewsIoU: 0.7573 -> 0.7590Improved
use progressive upsampling decoder instead of prior decoders (EVolT, LegoFormer, 3D-RETR) (ablation)LRGT · ShapeNet 3 viewsIoU: 0.7511-0.7576 -> 0.7590Improved
use full-range attention across all views' tokens (ablation)Multi-view transformer encoder · ShapeNet with 16-20 viewsIoUHurt
use token-range grouping attention instead of no inter-view attention (ablation)Multi-view transformer encoder · ShapeNetIoUHurt
use long-range grouping rather than short-range or random-range grouping (ablation)LRGT encoder · ShapeNet, varied viewsIoUImproved
use LGA and IFS on single-view Pix3D (ablation)LRGT · Pix3D single-viewIoU: 0.304 -> 0.299Hurt
train with 8 views (LRGT+) instead of 3 viewsLRGT · ShapeNet 1 view vs 20 viewsIoU: 1 view: 0.6962 -> 0.5847; 20 views: 0.7786 -> 0.7922Mixed

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