Point-to-Mask: From Arbitrary Point Annotations to Mask-Level Infrared Small Target Detection

arXiv cs.CV / 3/18/2026

📰 NewsTools & Practical UsageModels & Research

共有:

Key Points

The paper proposes Point-to-Mask, a framework that bridges low-cost point supervision and mask-level infrared small target detection using two modules: PAMG and RPR-Net.
PAMG converts point annotations into compact target masks and geometric cues to generate pseudo labels for training.
RPR-Net localizes target centers and regresses effective radii using spatiotemporal motion cues, reframing IRSTD as center localization plus radius regression.
The modules operate in a closed loop: PAMG's pseudo masks guide training and RPR-Net's geometric predictions refine masks during inference.
A new dataset, SIRSTD-Pixel, is introduced for pixel-level evaluation, and the approach achieves near full-supervision performance with much lower annotation cost, with code and data to be released.

Abstract

Infrared small target detection (IRSTD) methods predominantly formulate the task as pixel-level segmentation, which requires costly dense annotations and is not well suited to tiny targets with weak texture and ambiguous boundaries. To address this issue, we propose Point-to-Mask, a framework that bridges low-cost point supervision and mask-level detection through two components: a Physics-driven Adaptive Mask Generation (PAMG) module that converts point annotations into compact target masks and geometric cues, and a lightweight Radius-aware Point Regression Network (RPR-Net) that reformulates IRSTD as target center localization and effective radius regression using spatiotemporal motion cues. The two modules form a closed loop: PAMG generates pseudo masks and geometric supervision during training, while the geometric predictions of RPR-Net are fed back to PAMG for pixel-level mask recovery during inference. To facilitate systematic evaluation, we further construct SIRSTD-Pixel, a sequential dataset with refined pixel-level annotations. Experiments show that the proposed framework achieves strong pseudo-label quality, high detection accuracy, and efficient inference, approaching full-supervision performance under point-supervised settings with substantially lower annotation cost. Code and datasets will be available at: https://github.com/GaoScience/point-to-mask.