AI Paper Atlas

Research map / Point clouds / Shape and surface completion

DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction

Yuxin Yao, Siyu Ren, Junhui Hou, Zhi Deng, Juyong Zhang, Wenping Wang

ECCV 2024 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 4 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 learnable control-point deformation with pointwise MLP deformation (ablation)DynoSurf · AMA ablationCorr. error (x10^-2): 2.89 -> 5.91Hurt
learn blending weights instead of fixed Gaussian formula (ablation)DynoSurf · AMA ablationCD (x10^-4): 0.475 -> 0.324Improved
make control point positions learnable (ablation)DynoSurf · AMA ablationCD (x10^-4): 0.372 -> 0.324Improved
add normal consistency loss in temporal reconstruction (ablation)DynoSurf · AMA ablationCD (x10^-4): 0.656 -> 0.324Improved
add deformation smoothness loss (ablation)DynoSurf · AMA ablationCD (x10^-4): 0.378 -> 0.324Improved
add robust SDF loss (ablation)DynoSurf · AMA ablationCD (x10^-4): CD 0.330 -> 0.324, Corr. 3.14 -> 2.89Mixed
add shape preservation loss (ablation)DynoSurf · AMA ablationCD (x10^-4): 0.335 -> 0.324 (Corr. 2.91 -> 2.89)Mixed
increase control points from 10 to 30 (ablation)DynoSurf · AMA ablationCD (x10^-4): 0.437 -> 0.324Improved
increase control points from 30 to 100 (ablation)DynoSurf · AMA ablationCorr. error (x10^-2): CD 0.324 -> 0.315, Corr. 2.89 -> 3.16Mixed
use ground-truth normals instead of estimated normals (ablation)DynoSurf · AMACD (x10^-4): 0.324 -> 0.318No clear effect
increase input sequence length from 30 to 80 frames (ablation)DynoSurf · DFAUST shake_shouldersCD (x10^-4): 0.138 -> 0.265Hurt
reduce input points per frame from 5000 to 2000 (ablation)DynoSurf · AMACD (x10^-4): 0.324 -> 0.451Hurt

Later papers that compared with this method

1 later accepted paper reports DynoSurf as a baseline in their results tables; 1 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