AI Paper Atlas

Research map / 3D vision / Face and shape

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

Gengshan Yang, Deqing Sun, Varun Jampani, Daniel Vlasic, Forrester Cole, Ce Liu, Deva Ramanan

NeurIPS 2021 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 35 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 3D matching loss (ablation)ViSER · break-1keypoint transfer accuracy: 36.2 -> 70.5Improved
add 3D matching loss (ablation)ViSER · Elephants innerkeypoint transfer accuracy: 51.3 -> 80.4Improved
add 3D matching loss (ablation)ViSER · Elephants crosskeypoint transfer accuracy: 42.6 -> 68.9Improved
add 2D cycle reprojection loss (ablation)ViSER · break-1keypoint transfer accuracy: 38.3 -> 70.5Improved
add 2D cycle reprojection loss (ablation)ViSER · Elephants crosskeypoint transfer accuracy: 62.5 -> 68.9Improved
add 2D cycle reprojection loss (ablation)ViSER · Elephants innerkeypoint transfer accuracy: 80.1 -> 80.4No clear effect
use pixel-surface embedding matching instead of CSM regression (ablation)ViSER · break-1keypoint transfer accuracy: 47.1 -> 70.5Improved
use pixel-surface embedding matching instead of CSM regression (ablation)ViSER · Elephants innerkeypoint transfer accuracy: 77.4 -> 80.4Improved
use ViSER instead of template-based methods on tight-clothing common posesViSER vs DensePose CSE · parkourkeypoint transfer accuracy: 85.9 -> 62.9Hurt

Later papers that compared with this method

4 later accepted papers report ViSER as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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