AI Paper Atlas

Research map / 3D vision / Face and shape

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

Christopher B. Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, Silvio Savarese

ECCV 2016 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 1,765 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 GRU units instead of LSTM units (1x1x1 conv) (ablation)3D-R2N2 · ShapeNet test (5 views)voxel IoU: 0.499 -> 0.540Improved
use GRU units instead of LSTM units (3x3x3 conv) (ablation)3D-R2N2 · ShapeNet test (5 views)voxel IoU: 0.539 -> 0.592Improved
use 3x3x3 convolution (neighboring recurrent connections) instead of 1x1x1 for GRU (ablation)3D-R2N2 · ShapeNet test (5 views)voxel IoU: 0.540 -> 0.592Improved
use 3x3x3 convolution instead of 1x1x1 for LSTM (ablation)3D-R2N2 · ShapeNet test (5 views)voxel IoU: 0.499 -> 0.539Improved
replace simple encoder/decoder with deep residual encoder/decoder (ablation)3D-GRU-3 · ShapeNet test (5 views)voxel IoU: 0.592 -> 0.634Improved
same residual change measured by loss (ablation)3D-GRU-3 · ShapeNet test (5 views)cross-entropy loss: 0.091 -> 0.080Improved
use Res3D-GRU-3 instead of Kar et al. (which also gets masks and keypoints)PASCAL VOC single view · PASCAL VOC (PASCAL 3D+), meanvoxel IoU: 0.318 -> 0.571Improved
use LSTM-1 network instead of Kar et al.PASCAL VOC single view · PASCAL VOC (PASCAL 3D+), meanvoxel IoU: 0.318 -> 0.456Improved
increase views from 1 to 5 (car) (ablation)Res3D-GRU-3 · ShapeNet test, carvoxel IoU: 0.798 -> 0.836Improved
increase views from 1 to 5 (lamp) (ablation)Res3D-GRU-3 · ShapeNet test, lampvoxel IoU: 0.381 -> 0.421Improved
increase views from 1 to 5 (chair) (ablation)Res3D-GRU-3 · ShapeNet test, chairvoxel IoU: 0.466 -> 0.550Improved
use 3D-R2N2 instead of MVS with fewer than 20 views3D-R2N2 vs PatchMatch MVS · synthetic CAD models, various texturevoxel IoU: MVS IoU=0 when fewer than 20 viewsImproved

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