AI Paper Atlas

Research map / 3D vision / Face and shape

Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval From a Single Image

Weicheng Kuo, Anelia Angelova, Tsung-Yi Lin, Angela Dai

ICCV 2021 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 35 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
replace whole-shape embedding with patch-wise embedding (Patch2CAD vs Mask2CAD)Mask2CAD · ScanNet 25Kmesh AP: 8.4 -> 10.3Improved
replace whole-shape embedding with patch-wise embedding, ground-truth 2D detectionsMask2CAD · ScanNet 25K (ground-truth 2D detections)mesh AP: 10.5 -> 12.9Improved
patch-wise embedding evaluated on shape only (F-score)Mask2CAD · ScanNet 25K (GT detections and pose, shape only)mean F-score: 60.6 -> 63.8Improved
patch-wise embedding on Pix3D with exact CAD matchesMask2CAD · Pix3D S1mesh AP: 33.2 -> 30.9Hurt
patch-wise embedding vs generative Mesh R-CNN on Pix3DMesh R-CNN · Pix3D S1mesh AP: 17.2 -> 30.9Improved
use patches of 1.0 (full object) with normals instead of Mask2CAD (ablation)Mask2CAD · ScanNet 25K (patch size ablation)mesh AP: 8.4 -> 9.4Improved
reduce patch size from 1.0 to 0.33 of ROI (ablation)Patch2CAD · ScanNet 25K (patch size ablation)mesh AP: 9.4 -> 10.3Improved
reduce patch size from 0.33 to 0.25 (ablation)Patch2CAD · ScanNet 25K (patch size ablation)mesh AP: 10.3 -> 10.0Hurt
increase query patches Kq from 1 to 9 (ablation)Patch2CAD · ScanNet 25K (test-time query patches Kq)mesh AP: 9.2 -> 10.3Improved
increase Kq from 9 to 12 (ablation)Patch2CAD · ScanNet 25K (test-time query patches Kq)mesh AP: 10.3 -> 10.2No clear effect
increase retrieved patches Kr from 1 to 48 (ablation)Patch2CAD · ScanNet 25K (test-time retrieved patches Kr)mesh AP: 9.3 -> 10.6Improved
increase Kr from 48 to 96 (ablation)Patch2CAD · ScanNet 25K (test-time retrieved patches Kr)mesh AP: 10.6 -> 10.6No 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