The reviewed record of science sign in
Pith

arxiv: 2505.17649 · v1 · pith:KQ45RD6X · submitted 2025-05-23 · cs.CV

Instruct2See: Learning to Remove Any Obstructions Across Distributions

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:KQ45RD6Xrecord.jsonopen to challenge →

classification cs.CV
keywords instruct2seeobstaclesobstructionmaskobstructionsremovalachievesacross
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. V2XCrafter: Learning to Generate Driving Scene Across Agents

    cs.CV 2026-05 unverdicted novelty 6.0

    V2XCrafter introduces a progressive multi-agent diffusion model with cross-agent attention to generate controllable, consistent collaborative driving scenes for V2X data augmentation.