Occlusion-Aware Temporally Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Doh, Hyungjun, Lee, Dong In, Chi, Seunggeun, Huang, Pin-Hao, Lee, Kwonjoon, Kim, Sangpil, Ramani, Karthik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915493234868224
author Doh, Hyungjun
Lee, Dong In
Chi, Seunggeun
Huang, Pin-Hao
Lee, Kwonjoon
Kim, Sangpil
Ramani, Karthik
author_facet Doh, Hyungjun
Lee, Dong In
Chi, Seunggeun
Huang, Pin-Hao
Lee, Kwonjoon
Kim, Sangpil
Ramani, Karthik
contents We introduce a novel framework for reconstructing dynamic human-object interactions from monocular video that overcomes challenges associated with occlusions and temporal inconsistencies. Traditional 3D reconstruction methods typically assume static objects or full visibility of dynamic subjects, leading to degraded performance when these assumptions are violated-particularly in scenarios where mutual occlusions occur. To address this, our framework leverages amodal completion to infer the complete structure of partially obscured regions. Unlike conventional approaches that operate on individual frames, our method integrates temporal context, enforcing coherence across video sequences to incrementally refine and stabilize reconstructions. This template-free strategy adapts to varying conditions without relying on predefined models, significantly enhancing the recovery of intricate details in dynamic scenes. We validate our approach using 3D Gaussian Splatting on challenging monocular videos, demonstrating superior precision in handling occlusions and maintaining temporal stability compared to existing techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08137
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Occlusion-Aware Temporally Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction
Doh, Hyungjun
Lee, Dong In
Chi, Seunggeun
Huang, Pin-Hao
Lee, Kwonjoon
Kim, Sangpil
Ramani, Karthik
Computer Vision and Pattern Recognition
Artificial Intelligence
We introduce a novel framework for reconstructing dynamic human-object interactions from monocular video that overcomes challenges associated with occlusions and temporal inconsistencies. Traditional 3D reconstruction methods typically assume static objects or full visibility of dynamic subjects, leading to degraded performance when these assumptions are violated-particularly in scenarios where mutual occlusions occur. To address this, our framework leverages amodal completion to infer the complete structure of partially obscured regions. Unlike conventional approaches that operate on individual frames, our method integrates temporal context, enforcing coherence across video sequences to incrementally refine and stabilize reconstructions. This template-free strategy adapts to varying conditions without relying on predefined models, significantly enhancing the recovery of intricate details in dynamic scenes. We validate our approach using 3D Gaussian Splatting on challenging monocular videos, demonstrating superior precision in handling occlusions and maintaining temporal stability compared to existing techniques.
title Occlusion-Aware Temporally Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.08137