AI Paper Atlas

Research map / 3D vision / Face and shape

TokenHand: Discrete Token Representation for Efficient Hand Mesh Reconstruction

Xinguo He, Yixin Shen, Rahul Chaudhari

CVPR 2026 · 3D vision › Face and shape · approach: Pixel-aligned implicit human and hand reconstruction

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
increase regressor layers from 1 to 4 with progressive x2 token counts (ablation)TokenHand decoder · FreiHAND testPA-MPJPE (mm): 6.4 -> 5.7Improved
use non-progressive token counts [48,128,256,512] instead of [48,97,194,389] (ablation)TokenHand decoder · FreiHAND testPA-MPJPE (mm): 5.7 -> 5.9Hurt
reduce feature dimensions toward 16 instead of 32 (ablation)TokenHand decoder · FreiHAND testPA-MPJPE (mm): 5.7 -> 5.9Hurt
increase MetaFormer blocks per regressor layer from 1 to 3 (ablation)TokenHand decoder · FreiHAND testPA-MPJPE (mm): 5.7 -> 5.8No clear effect
change codebook size (384x512, 640x512 vs 512x512) (ablation)TokenHand Stage I · FreiHANDPA-MPJPE (mm): 4.9 -> 5.1 (640x512)No clear effect
switch backbone from ResNet50 to FastViT-MA36 (ablation)TokenHand · FreiHAND testPA-MPJPE (mm): 6.7 -> 5.7Improved
use global pooled feature as token feature instead of keypoint-guided sampling on upsampled features (ablation)TokenHand token generator · FreiHAND testPA-MPJPE (mm): 5.7 -> 6.2Hurt
add 4x upsampling before keypoint-guided sampling (ablation)TokenHand token generator · FreiHAND testPA-MPJPE (mm): 6.0 -> 5.7Improved
add convolutional enhancement of upsampled features (ablation)TokenHand token generator · FreiHAND testPA-MPJPE (mm): 5.7 -> 5.7No clear effect
replace keypoint-based sampling with coarse-mesh sampling (ablation)TokenHand token generator · FreiHAND testPA-MPJPE (mm): 5.7 -> 5.8No clear effect
discrete token classification with lightweight decoder instead of transformer regressionhand mesh reconstruction · FreiHAND test#Params (decoder): 98M -> 3.0M vs MeshGraphormerImproved
use TokenHand instead of FastViTFastViT-MA36 backbone · FreiHAND testFPS: 84 -> 65Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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