AI Paper Atlas

Research map / 3D vision / Face and shape

Learning 3D Object Categories by Looking Around Them

David Novotny, Diane Larlus, Andrea Vedaldi

ICCV 2017 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 63 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 probabilistic losses and confidence prediction (ablation)VpDR-Net · chair, LDOSangular error eR: 45.33 -> 33.92Improved
add probabilistic losses and confidence prediction (ablation)VpDR-Net · chair, Pascal3Dangular error eR: 57.23 -> 42.34Improved
add depth and point cloud prediction branches during training (ablation)VpDR-Net · chair, LDOSangular error eR: 68.19 -> 33.92Improved
add depth and point cloud prediction branches during training (ablation)VpDR-Net · chair, Pascal3Dangular error eR: 60.31 -> 42.34Improved
add geometry-aware data augmentation (ablation)VpDR-Net · chair, LDOSangular error eR: 35.16 -> 33.92Improved
add geometry-aware data augmentation (ablation)VpDR-Net · chair, Pascal3Dangular error eR: 43.52 -> 42.34Improved
add geometry-aware data augmentation (ablation)VpDR-Net · chair, Pascal3DAPeR: 0.10 -> 0.23Improved
use viewpoint factorization training instead of aligning shapes in 3DVpDR-Net vs VPNet-unsupervised · car, Pascal3Dangular error eR: 49.62 -> 29.57Improved
use viewpoint factorization training instead of aligning shapes in 3DVpDR-Net vs VPNet-unsupervised · chair, LDOSangular error eR: 30.56 -> 33.92Hurt
use VpDR-Net confidence instead of VPNet softmax confidenceVpDR-Net · car, Pascal3DAPeC: 0.01 -> 0.91Improved
predict point clouds with VpDR-Net instead of retrieval (Aubry)VpDR-Net · LDOS chairs point cloudmDpcl: 1.30 -> 0.20Improved
fuse predicted point cloud with partial depth point cloudVpDR-Net-Fuse · FrC cars point cloudmDpcl: 0.28 -> 0.26Improved

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