AI Paper Atlas

Research map / 3D vision / Face and shape

Recurrent Multi-View Alignment Network for Unsupervised Surface Registration

Wanquan Feng, Juyong Zhang, Hongrui Cai, Haofei Xu, Junhui Hou, Hujun Bao

CVPR 2021 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 54 citations (OpenAlex)

Check 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
Represent non-rigid deformation using recurrently added rigid transforms with learned point-wise weightsRMA-Net · DeformCD: 2.375 -> 0.599Improved
Use recurrently added rigid transforms with learned point-wise weightsRMA-Net · DeformEMD: 5.478 -> 0.386Improved
Use multi-view depth and mask loss instead of Chamfer loss (ablation)RMA-Net · Deformable objectsCD: 1.652 -> 0.599Improved
Use multi-view depth and mask loss instead of EMD loss (ablation)RMA-Net · Deformable objectsCD: 3.241 -> 0.599Improved
Add mask loss to depth loss (ablation)RMA-Net · Deformable objectsCD: 0.701 -> 0.691Improved
Increase views from 5^2 to 7^2 (ablation)RMA-Net · Deformable objectsCD: 0.691 -> 0.618Improved
Increase views from 7^2 to 9^2 (ablation)RMA-Net · Deformable objectsCD: 0.618 -> 0.600Improved
Increase recurrent stages from 3 to 7 (ablation)RMA-Net · Deformable objectsCD: 10.717 -> 0.599Improved
Use ground-truth supervision instead of unsupervised trainingRMA-Net · ModelNet40RMSE(R): 1.287 -> 0.735Improved
Use ground-truth supervision instead of unsupervised trainingRMA-Net · ModelNet40MAE(t): 0.007 -> 0.009Hurt
Apply RMA-Net to raw scanned surfaces with noise, outliers, and incompletenessRMA-Net · DFAUSTCD: 0.43 -> 0.24Improved

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