Research map / 3D vision / Human pose estimation
HOPE: Hand-Object Pressure Estimation from Monocular Videos
Subin Jeon, Byungjun Kim, Hanbyul Joo
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Formulates hand-object pressure estimation as a hand-centric video prediction problem, predicting per-MANO-vertex pressure from monocular video via a unified annotation pipeline and a contact-gated VertexFormer.
Problem
Vision-based pressure estimation is largely limited to planar surfaces and single images, and does not handle dynamic hand-object interaction with diverse objects.
Approach
Frames pressure estimation as hand-centric video prediction over MANO hand-mesh vertices, unifying heterogeneous supervision (tactile sensors, contact annotations) into per-vertex pressure labels, and predicts them with a transformer (VertexFormer) gated by estimated contact.
Experimental setup
Datasets: OpenTouch PressureVisionDB DexYCB ARCTIC MOW
Benchmarks: OpenTouch PressureVisionDB DexYCB ARCTIC MOW
Baselines: PressureVision
Builds on: MANO HaWoR
Closest papers by meaning
- PressureVision: Estimating Hand Pressure from a Single RGB Image (ECCV 2022 · similarity 0.91)
- EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision (CVPR 2025 · similarity 0.91)
- EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video (ICML 2026 · similarity 0.90)
- Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation (NeurIPS 2024 · similarity 0.87)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.87)
- StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video (NeurIPS 2026 · similarity 0.87)
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.
