AI Paper Atlas

Research map / 3D vision / Face and shape

C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion

David Novotny, Nikhila Ravi, Benjamin Graham, Natalia Neverova, Andrea Vedaldi

ICCV 2019 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 98 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 canonicalization network and in-plane rotation loss to C3DPO-base (ablation)C3DPO · S-Up3DMPJPE: 0.160 -> 0.068Improved
add canonicalization network on top of C3DPO-equiv (ablation)C3DPO · S-Up3DMPJPE: 0.154 -> 0.068Improved
add in-plane rotation invariant loss to C3DPO-base (ablation)C3DPO-base · S-Up3DMPJPE: 0.160 -> 0.154Improved
add canonicalization network on top of C3DPO-equiv (ablation)C3DPO · PASCAL3D+ (12 classes, GT keypoints at test)MPJPE: 50.1 -> 38.0Improved
add in-plane rotation invariant loss to C3DPO-base (ablation)C3DPO-base · PASCAL3D+ (12 classes, GT keypoints at test)MPJPE: 53.5 -> 50.1Improved
add canonicalization network on top of C3DPO-equiv (ablation)C3DPO · Human3.6M (ground truth 2D keypoints)MPJPE: 128.2 -> 101.8Improved
add canonicalization network on top of C3DPO-equiv (ablation)C3DPO · Human3.6M (Stacked Hourglass keypoints)MPJPE: 190.4 -> 153.0Improved
add in-plane rotation invariant loss to C3DPO-base (ablation)C3DPO-base · Human3.6M (Stacked Hourglass keypoints)MPJPE: 201.6 -> 190.4Improved
use C3DPO-base instead of Pose-GAN with ground truth keypoints (re-projection loss only)C3DPO-base · Human3.6M (ground truth 2D keypoints)MPJPE: 130.9 -> 135.2Hurt
use C3DPO + HRNet instead of CMRC3DPO · PASCAL3D+ (12 classes, predicted keypoints)MPJPE: 74.4 -> 57.5Improved
use C3DPO instead of GbNrSfMNR-SFM baseline · PASCAL3D+ (12 classes, GT keypoints at test)MPJPE: 184.6 -> 38.0Improved
use C3DPO instead of EM-SfM on S-Up3DNR-SFM baseline · S-Up3DMPJPE: 0.107 -> 0.068Improved

Later papers that compared with this method

6 later accepted papers report C3dpo as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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