Saved in:
Bibliographic Details
Main Authors: Li, Junhang, Guo, Yu, Xian, Chuhua, He, Shengfeng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.17649
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908376336695296
author Li, Junhang
Guo, Yu
Xian, Chuhua
He, Shengfeng
author_facet Li, Junhang
Guo, Yu
Xian, Chuhua
He, Shengfeng
contents Images are often obstructed by various obstacles due to capture limitations, hindering the observation of objects of interest. Most existing methods address occlusions from specific elements like fences or raindrops, but are constrained by the wide range of real-world obstructions, making comprehensive data collection impractical. To overcome these challenges, we propose Instruct2See, a novel zero-shot framework capable of handling both seen and unseen obstacles. The core idea of our approach is to unify obstruction removal by treating it as a soft-hard mask restoration problem, where any obstruction can be represented using multi-modal prompts, such as visual semantics and textual instructions, processed through a cross-attention unit to enhance contextual understanding and improve mode control. Additionally, a tunable mask adapter allows for dynamic soft masking, enabling real-time adjustment of inaccurate masks. Extensive experiments on both in-distribution and out-of-distribution obstacles show that Instruct2See consistently achieves strong performance and generalization in obstruction removal, regardless of whether the obstacles were present during the training phase. Code and dataset are available at https://jhscut.github.io/Instruct2See.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17649
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Instruct2See: Learning to Remove Any Obstructions Across Distributions
Li, Junhang
Guo, Yu
Xian, Chuhua
He, Shengfeng
Computer Vision and Pattern Recognition
Images are often obstructed by various obstacles due to capture limitations, hindering the observation of objects of interest. Most existing methods address occlusions from specific elements like fences or raindrops, but are constrained by the wide range of real-world obstructions, making comprehensive data collection impractical. To overcome these challenges, we propose Instruct2See, a novel zero-shot framework capable of handling both seen and unseen obstacles. The core idea of our approach is to unify obstruction removal by treating it as a soft-hard mask restoration problem, where any obstruction can be represented using multi-modal prompts, such as visual semantics and textual instructions, processed through a cross-attention unit to enhance contextual understanding and improve mode control. Additionally, a tunable mask adapter allows for dynamic soft masking, enabling real-time adjustment of inaccurate masks. Extensive experiments on both in-distribution and out-of-distribution obstacles show that Instruct2See consistently achieves strong performance and generalization in obstruction removal, regardless of whether the obstacles were present during the training phase. Code and dataset are available at https://jhscut.github.io/Instruct2See.
title Instruct2See: Learning to Remove Any Obstructions Across Distributions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.17649