Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Jiangyuan, Ma, Hongxuan, Guo, Yuxin, Zhao, Yuhao, Zhang, Chi, Sui, Wei, Zou, Wei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929739533385728
author Liu, Jiangyuan
Ma, Hongxuan
Guo, Yuxin
Zhao, Yuhao
Zhang, Chi
Sui, Wei
Zou, Wei
author_facet Liu, Jiangyuan
Ma, Hongxuan
Guo, Yuxin
Zhao, Yuhao
Zhang, Chi
Sui, Wei
Zou, Wei
contents Transparent object perception is indispensable for numerous robotic tasks. However, accurately segmenting and estimating the depth of transparent objects remain challenging due to complex optical properties. Existing methods primarily delve into only one task using extra inputs or specialized sensors, neglecting the valuable interactions among tasks and the subsequent refinement process, leading to suboptimal and blurry predictions. To address these issues, we propose a monocular framework, which is the first to excel in both segmentation and depth estimation of transparent objects, with only a single-image input. Specifically, we devise a novel semantic and geometric fusion module, effectively integrating the multi-scale information between tasks. In addition, drawing inspiration from human perception of objects, we further incorporate an iterative strategy, which progressively refines initial features for clearer results. Experiments on two challenging synthetic and real-world datasets demonstrate that our model surpasses state-of-the-art monocular, stereo, and multi-view methods by a large margin of about 38.8%-46.2% with only a single RGB input. Codes and models are publicly available at https://github.com/L-J-Yuan/MODEST.
format Preprint
id arxiv_https___arxiv_org_abs_2502_14616
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion
Liu, Jiangyuan
Ma, Hongxuan
Guo, Yuxin
Zhao, Yuhao
Zhang, Chi
Sui, Wei
Zou, Wei
Computer Vision and Pattern Recognition
Transparent object perception is indispensable for numerous robotic tasks. However, accurately segmenting and estimating the depth of transparent objects remain challenging due to complex optical properties. Existing methods primarily delve into only one task using extra inputs or specialized sensors, neglecting the valuable interactions among tasks and the subsequent refinement process, leading to suboptimal and blurry predictions. To address these issues, we propose a monocular framework, which is the first to excel in both segmentation and depth estimation of transparent objects, with only a single-image input. Specifically, we devise a novel semantic and geometric fusion module, effectively integrating the multi-scale information between tasks. In addition, drawing inspiration from human perception of objects, we further incorporate an iterative strategy, which progressively refines initial features for clearer results. Experiments on two challenging synthetic and real-world datasets demonstrate that our model surpasses state-of-the-art monocular, stereo, and multi-view methods by a large margin of about 38.8%-46.2% with only a single RGB input. Codes and models are publicly available at https://github.com/L-J-Yuan/MODEST.
title Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.14616