Papers › Harmonious Feature Learning for Interactive Hand-Object Pose Estimation

Harmonious Feature Learning for Interactive Hand-Object Pose Estimation

1 Jan 2023CVPR 2023 1archive 2025-07-28

Zhifeng Lin, Changxing Ding, Huan Yao, Zengsheng Kuang, Shaoli Huang

Joint hand and object pose estimation from a single image is extremely challenging as serious occlusion often occurs when the hand and object interact. Existing approaches typically first extract coarse hand and object features from a single backbone, then further enhance them with reference to each other via interaction modules. However, these works usually ignore that the hand and object are competitive in feature learning, since the backbone takes both of them as foreground and they are usually mutually occluded. In this paper, we propose a novel Harmonious Feature Learning Network (HFL-Net). HFL-Net introduces a new framework that combines the advantages of single- and double-stream backbones: it shares the parameters of the low- and high-level convolutional layers of a common ResNet-50 model for the hand and object, leaving the middle-level layers unshared. This strategy enables the hand and the object to be extracted as the sole targets by the middle-level layers, avoiding their competition in feature learning. The shared high-level layers also force their features to be harmonious, thereby facilitating their mutual feature enhancement. In particular, we propose to enhance the feature of the hand via concatenation with the feature in the same location from the object stream. A subsequent self-attention layer is adopted to deeply fuse the concatenated feature. Experimental results show that our proposed approach consistently outperforms state-of-the-art methods on the popular HO3D and Dex-YCB databases. Notably, the performance of our model on hand pose estimation even surpasses that of existing works that only perform the single-hand pose estimation task. Code is available at https://github.com/lzfff12/HFL-Net.

PaperPDFCode

Code

lzfff12/hfl-net officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Hand Pose EstimationHand Pose EstimationObjectPose Estimationhand-object pose

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation DexYCB HFLNet Average MPJPE (mm) 12.6 #4 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HFLNet MPVPE 11.6 #4 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HFLNet PA-MPVPE 5.2 #4 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HFLNet PA-VAUC 89.6 #4 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HFLNet Procrustes-Aligned MPJPE 5.47 #4 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HFLNet VAUC 77.6 #4 of 11 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 HFL-Net F@15mm 0.965 #9 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 HFL-Net F@5mm 0.575 #9 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 HFL-Net PA-MPJPE (mm) 8.9 #9 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 HFL-Net PA-MPVPE 8.7 #9 of 24 Archive leaderboard report
hand-object pose DexYCB HFL-Net ADD-S 31.9 #2 of 9 Archive leaderboard report
hand-object pose DexYCB HFL-Net Average MPJPE (mm) 11.9 #2 of 9 Archive leaderboard report
hand-object pose DexYCB HFL-Net MCE 45.7 #2 of 9 Archive leaderboard report
hand-object pose DexYCB HFL-Net OCE 39.8 #2 of 9 Archive leaderboard report
hand-object pose DexYCB HFL-Net Procrustes-Aligned MPJPE 5.81 #2 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HFL-Net ADD-S 32.4 #6 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HFL-Net Average MPJPE (mm) 28.9 #6 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HFL-Net OME 64.3 #6 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HFL-Net PA-MPJPE 8.9 #6 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HFL-Net ST-MPJPE 28.4 #6 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections