Awesome work on Hand-Object Interaction Synthesis and Reconstruction

• ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation (3dv 2024)

  • github: (https://eth-ait.github.io/artigrasp/)
  • main idea: bi-manual hand-object interactions(grasping and articulation) || curriculum learning || Reinforcement learning
  • disadvantage: focuses on a few grasping and articulation tasks and objects

• GraspXL: Generating Grasping Motions for Diverse Objects at Scale

  • github: https://github.com/zdchan/graspxl
  • main idea: Generating Grasping Motions for Diverse Objects at Scale
  • disadvantage: single hand,

• InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion (CVPR 2024)

  • github: (https://github.com/jyunlee/InterHandGen)
  • main idea: (1) decompose the modeling of joint distribution. (2) Combine anti-penetration and classifier-free guidance to enable plausible generation.

• HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 Highlight)

  • github: (https://github.com/zc-alexfan/hold)
  • main idea: the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data.

• HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data (CVPR 2024)

  • github: https://github.com/Mq-Zhang1/HOIDiffusion
  • main idea: controllable(eg. object, baackground) and realistic Hand-Object Interaction image synthesis

• GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion (ICLR 2024)

  • webpage: https://meowuu7.github.io/GeneOH-Diffusion/
  • main idea: contact-centric representation, focus on hand trajectory

• DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions (SIGGRAPH Asia 2024)

  • webpage: https://diffh2o.github.io/

• ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion

  • paper: https://www.arxiv.org/pdf/2409.09300

• DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes

  • paper: https://openreview.net/pdf?id=V6XHKFicwc