Saved in:
Bibliographic Details
Main Authors: Prakash, Aditya, Forsyth, David, Gupta, Saurabh
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.06145
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916994912092160
author Prakash, Aditya
Forsyth, David
Gupta, Saurabh
author_facet Prakash, Aditya
Forsyth, David
Gupta, Saurabh
contents We tackle the problem of forecasting bimanual 3D hand motion & articulation from a single image in everyday settings. To address the lack of 3D hand annotations in diverse settings, we design an annotation pipeline consisting of a diffusion model to lift 2D hand keypoint sequences to 4D hand motion. For the forecasting model, we adopt a diffusion loss to account for the multimodality in hand motion distribution. Extensive experiments across 6 datasets show the benefits of training on diverse data with imputed labels (14% improvement) and effectiveness of our lifting (42% better) & forecasting (16.4% gain) models, over the best baselines, especially in zero-shot generalization to everyday images.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06145
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bimanual 3D Hand Motion and Articulation Forecasting in Everyday Images
Prakash, Aditya
Forsyth, David
Gupta, Saurabh
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
We tackle the problem of forecasting bimanual 3D hand motion & articulation from a single image in everyday settings. To address the lack of 3D hand annotations in diverse settings, we design an annotation pipeline consisting of a diffusion model to lift 2D hand keypoint sequences to 4D hand motion. For the forecasting model, we adopt a diffusion loss to account for the multimodality in hand motion distribution. Extensive experiments across 6 datasets show the benefits of training on diverse data with imputed labels (14% improvement) and effectiveness of our lifting (42% better) & forecasting (16.4% gain) models, over the best baselines, especially in zero-shot generalization to everyday images.
title Bimanual 3D Hand Motion and Articulation Forecasting in Everyday Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.06145