Research map / 3D vision / Human pose estimation
HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton
Wencan Cheng, Jae Hyun Park, Jong Hwan Ko
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add one local folding block after global folding (ablation) | HandFoldingNet · ICVL | mean distance error (mm): 8.13 -> 6.34 | Improved |
| add a second local folding block (ablation) | HandFoldingNet · ICVL | mean distance error (mm): 6.34 -> 5.95 | Improved |
| add a third local folding block (ablation) | HandFoldingNet · ICVL | mean distance error (mm): 5.95 -> 6.08 | Hurt |
| add local features to the aggregated map (ablation) | HandFoldingNet · ICVL | mean distance error (mm): 7.90 -> 5.95 | Improved |
| add spatial dependency (rearranged embeddings) (ablation) | HandFoldingNet · ICVL | mean distance error (mm): 6.35 -> 5.95 | Improved |
| use first set abstraction level instead of raw input points for local grouping (ablation) | HandFoldingNet · ICVL | mean distance error (mm): 6.58 -> 5.95 | Improved |
| use first instead of second set abstraction level for local grouping (ablation) | HandFoldingNet · ICVL | mean distance error (mm): 6.48 -> 5.95 | Improved |
Later papers that compared with this method
1 later accepted paper reports HandFoldingNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild (AAAI 2023 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- HandPointNet — Hand PointNet: 3D Hand Pose Estimation Using Point Sets (CVPR 2018) · better on 4 of 4 shared results
- JGR-P2O — JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image (ECCV 2020) · better on 2 of 3 shared results
- CrossInfoNet — CrossInfoNet: Multi-Task Information Sharing Based Hand Pose Estimation (CVPR 2019) · better on 3 of 3 shared results
- V2V-PoseNet — V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth Map (CVPR 2018) · better on 2 of 2 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
- Hand PointNet: 3D Hand Pose Estimation Using Point Sets (CVPR 2018 · similarity 0.92)
- End-to-End Detection and Pose Estimation of Two Interacting Hands (ICCV 2021 · similarity 0.90)
- SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation With Semi-Supervised Learning (ICCV 2019 · similarity 0.90)
- DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features (CVPR 2016 · similarity 0.90)
- Real-Time 3D Hand Pose Estimation with 3D Convolutional Neural Networks (TPAMI 2018 · similarity 0.90)
- 3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images (CVPR 2017 · similarity 0.90)
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.
