Saved in:
Bibliographic Details
Main Authors: On, Jeongwan, Gwak, Kyeonghwan, Kang, Gunyoung, Hwang, Hyein, Hwang, Soohyun, Cha, Junuk, Han, Jaewook, Baek, Seungryul
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.19215
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914966382051328
author On, Jeongwan
Gwak, Kyeonghwan
Kang, Gunyoung
Hwang, Hyein
Hwang, Soohyun
Cha, Junuk
Han, Jaewook
Baek, Seungryul
author_facet On, Jeongwan
Gwak, Kyeonghwan
Kang, Gunyoung
Hwang, Hyein
Hwang, Soohyun
Cha, Junuk
Han, Jaewook
Baek, Seungryul
contents This report describes our 1st place solution to the 8th HANDS workshop challenge (ARCTIC track) in conjunction with ECCV 2024. In this challenge, we address the task of bimanual category-agnostic hand-object interaction reconstruction, which aims to generate 3D reconstructions of both hands and the object from a monocular video, without relying on predefined templates. This task is particularly challenging due to the significant occlusion and dynamic contact between the hands and the object during bimanual manipulation. We worked to resolve these issues by introducing a mask loss and a 3D contact loss, respectively. Moreover, we applied 3D Gaussian Splatting (3DGS) to this task. As a result, our method achieved a value of 38.69 in the main metric, CD$_h$, on the ARCTIC test set.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19215
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 1st Place Solution to the 8th HANDS Workshop Challenge -- ARCTIC Track: 3DGS-based Bimanual Category-agnostic Interaction Reconstruction
On, Jeongwan
Gwak, Kyeonghwan
Kang, Gunyoung
Hwang, Hyein
Hwang, Soohyun
Cha, Junuk
Han, Jaewook
Baek, Seungryul
Computer Vision and Pattern Recognition
This report describes our 1st place solution to the 8th HANDS workshop challenge (ARCTIC track) in conjunction with ECCV 2024. In this challenge, we address the task of bimanual category-agnostic hand-object interaction reconstruction, which aims to generate 3D reconstructions of both hands and the object from a monocular video, without relying on predefined templates. This task is particularly challenging due to the significant occlusion and dynamic contact between the hands and the object during bimanual manipulation. We worked to resolve these issues by introducing a mask loss and a 3D contact loss, respectively. Moreover, we applied 3D Gaussian Splatting (3DGS) to this task. As a result, our method achieved a value of 38.69 in the main metric, CD$_h$, on the ARCTIC test set.
title 1st Place Solution to the 8th HANDS Workshop Challenge -- ARCTIC Track: 3DGS-based Bimanual Category-agnostic Interaction Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.19215