UV-Based 3D Hand-Object Reconstruction with Grasp Optimization
Not on the map. Why?
Abstract (arXiv)
We propose a novel framework for 3D hand shape reconstruction and hand-object grasp optimization from a single RGB image. The representation of hand-object contact regions is critical for accurate reconstructions. Instead of approximating the contact regions with sparse points, as in previous works, we propose a dense representation in the form of a UV coordinate map. Furthermore, we introduce inference-time optimization to fine-tune the grasp and improve interactions between the hand and the object. Our pipeline increases hand shape reconstruction accuracy and produces a vibrant hand texture. Experiments on datasets such as Ho3D, FreiHAND, and DexYCB reveal that our proposed method outperforms the state-of-the-art.
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 50 of its 70 references that are in the map. First posted on arXiv 24 Nov 2022.
Builds on
50 of 70 references.
References · 50
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
- 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
- 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
- 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
- 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
- 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
- 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
- 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 397
38 more
- 2019Learning joint reconstruction of hands and manipulated objectscited by 377
- 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 320
- 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
- 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
- 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
- 2021Mesh Graphormercited by 264
- 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
- 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
- 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
- 20193D Hand Shape and Pose from Images in the Wildcited by 190
- 2020ContactPose: A Dataset of Grasps with Object Contact and Hand Posecited by 180
- 2020Grasping Field: Learning Implicit Representations for Human Graspscited by 178
- 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
- 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
- 2020Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wildcited by 146
- 2020Reconstructing Hand-Object Interactions in the Wildcited by 143
- 2020Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstructioncited by 139
- 2020CPF: Learning a Contact Potential Field to Model the Hand-Object Interactioncited by 127
- 2015Capturing Hands in Action using Discriminative Salient Points and Physics Simulationcited by 115
- 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 109
- 2020Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraintscited by 97
- 2021ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesiscited by 76
- 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
- 20203D Human Mesh Regression with Dense Correspondencecited by 66
- 2021Model-based 3D Hand Reconstruction via Self-Supervised Learningcited by 65
- 2017UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognitioncited by 62
- 2018Online Model Distillation for Efficient Video Inferencecited by 60
- 2021Towards unconstrained joint hand-object reconstruction from RGB videoscited by 57
- 2021I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modelingcited by 52
- 2021A Skeleton-Driven Neural Occupancy Representation for Articulated Handscited by 50
- 2018Disentangling Latent Hands for Image Synthesis and Pose Estimationcited by 44
- 2018Exploring Spatial Context for 3D Semantic Segmentation of Point Cloudscited by 33
- 2021HO-3D_v3: Improving the Accuracy of Hand-Object Annotations of the HO-3D Datasetcited by 25
- 2019DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Imagecited by 20
- 20173DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Cloudscited by 12
- 2017Dynamics Based 3D Skeletal Hand Trackingcited by 10
- 2019Dual Grid Net: hand mesh vertex regression from single depth mapscited by 10
- 2020StyleUV: Diverse and High-fidelity UV Map Generative Modelcited by 6
Built on by
Citing papers per year: 2023: 2; 2024: 5; 2025: 1.
8 papers.
- 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
- 2024NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Modelcited by 10
- 2024MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wildcited by 5
- 2023Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstructioncited by 4
- 2023Nonrigid Object Contact Estimation With Regional Unwrapping Transformercited by 3
- 2024NCRF: Neural Contact Radiance Fields for Free-Viewpoint Rendering of Hand-Object Interactioncited by 1
- 2024A Versatile and Differentiable Hand-Object Interaction Representationcited by 1
- 2025TIGeR: Text-Instructed Generation and Refinement for Template-Free Hand-Object Interactioncited by 0
- 2025TIGeR: Text-Instructed Generation and Refinement for Template-Free Hand-Object Interaction1 Jun 2025
- 2024MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild18 Dec 2024
- 2024A Versatile and Differentiable Hand-Object Interaction Representation25 Sep 2024
- 2024NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model17 Jul 2024
- 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba12 Jul 2024
- 2024NCRF: Neural Contact Radiance Fields for Free-Viewpoint Rendering of Hand-Object Interaction8 Feb 2024
- 2023Nonrigid Object Contact Estimation With Regional Unwrapping Transformer27 Aug 2023
- 2023Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction1 May 2023