PALM: A Dataset and Baseline for Learning Multi-subject Hand Prior
Not on the map. Why?
Abstract (arXiv)
The ability to grasp objects, signal with gestures, and share emotion through touch all stem from the unique capabilities of human hands. Yet creating high-quality personalized hand avatars from images remains challenging due to complex geometry, appearance, and articulation, particularly under unconstrained lighting and limited views. Progress has also been limited by the lack of datasets that jointly provide accurate 3D geometry, high-resolution multiview imagery, and a diverse population of subjects. To address this, we present PALM, a large-scale dataset comprising 13k high-quality hand scans from 263 subjects and 90k multi-view images, capturing rich variation in skin tone, age, and geometry. To show its utility, we present a baseline PALM-Net, a multi-subject prior over hand geometry and material properties learned via physically based inverse rendering, enabling realistic, relightable single-image hand avatar personalization. PALM's scale and diversity make it a valuable real-world resource for hand modeling and related research.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 47 of its 58 references that are in the map. First posted on arXiv 7 Nov 2025.
Builds on
47 of 58 references.
References · 47
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2021Volume Rendering of Neural Implicit Surfacescited by 990
- 2020Implicit Geometric Regularization for Learning Shapescited by 707
- 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
- 2019Learning joint reconstruction of hands and manipulated objectscited by 377
- 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
- 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 320
- 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
- 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
- 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
- 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 251
35 more
- 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 244
- 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
- 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
- 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 229
- 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
- 2020ContactPose: A Dataset of Grasps with Object Contact and Hand Posecited by 180
- 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
- 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 122
- 2015Capturing Hands in Action using Discriminative Salient Points and Physics Simulationcited by 115
- 2020Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraintscited by 97
- 2017Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensorcited by 84
- 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 76
- 2022gDNA: Towards Generative Detailed Neural Avatarscited by 72
- 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
- 2024GraspXL: Generating Grasping Motions for Diverse Objects at Scalecited by 59
- 2021A Skeleton-Driven Neural Occupancy Representation for Articulated Handscited by 50
- 2024Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Cameracited by 50
- 2020DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modelingcited by 49
- 2017BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysiscited by 46
- 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
- 2022Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Videocited by 37
- 20163D Hand Pose Tracking and Estimation Using Stereo Matchingcited by 35
- 2023A Dataset of Relighted 3D Interacting Handscited by 35
- 2024Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objectscited by 35
- 2022HARP: Personalized Hand Reconstruction from a Monocular RGB Videocited by 28
- 2023LiveHand: Real-time and Photorealistic Neural Hand Renderingcited by 26
- 2022DART: Articulated Hand Model with Diverse Accessories and Rich Texturescited by 25
- 2023HMP: Hand Motion Priors for Pose and Shape Estimation from Videocited by 23
- 2023IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracingcited by 20
- 2024OHTA: One-shot Hand Avatar via Data-driven Implicit Priorscited by 18
- 2024URHand: Universal Relightable Handscited by 17
- 2025MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clipscited by 15
- 2024Authentic Hand Avatar from a Phone Scan via Universal Hand Modelcited by 13
- 2023Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Imagescited by 9
- 2023PHRIT: Parametric Hand Representation with Implicit Templatecited by 5
Built on by
Citing papers per year: 2026: 3.
3 papers.