PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bonazzi, Pietro, Farronato, Nicola, Zihlmann, Stefan, Qin, Haotong, Magno, Michele
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908642753642496
author Bonazzi, Pietro
Farronato, Nicola
Zihlmann, Stefan
Qin, Haotong
Magno, Michele
author_facet Bonazzi, Pietro
Farronato, Nicola
Zihlmann, Stefan
Qin, Haotong
Magno, Michele
contents Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications like smart glasses and IoT devices. We introduce PicoSAM2, a lightweight (1.3M parameters, 336M MACs) promptable segmentation model optimized for edge and in-sensor execution, including the Sony IMX500. It builds on a depthwise separable U-Net, with knowledge distillation and fixed-point prompt encoding to learn from the Segment Anything Model 2 (SAM2). On COCO and LVIS, it achieves 51.9% and 44.9% mIoU, respectively. The quantized model (1.22MB) runs at 14.3 ms on the IMX500-achieving 86 MACs/cycle, making it the only model meeting both memory and compute constraints for in-sensor deployment. Distillation boosts LVIS performance by +3.5% mIoU and +5.1% mAP. These results demonstrate that efficient, promptable segmentation is feasible directly on-camera, enabling privacy-preserving vision without cloud or host processing.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18807
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications
Bonazzi, Pietro
Farronato, Nicola
Zihlmann, Stefan
Qin, Haotong
Magno, Michele
Computer Vision and Pattern Recognition
Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications like smart glasses and IoT devices. We introduce PicoSAM2, a lightweight (1.3M parameters, 336M MACs) promptable segmentation model optimized for edge and in-sensor execution, including the Sony IMX500. It builds on a depthwise separable U-Net, with knowledge distillation and fixed-point prompt encoding to learn from the Segment Anything Model 2 (SAM2). On COCO and LVIS, it achieves 51.9% and 44.9% mIoU, respectively. The quantized model (1.22MB) runs at 14.3 ms on the IMX500-achieving 86 MACs/cycle, making it the only model meeting both memory and compute constraints for in-sensor deployment. Distillation boosts LVIS performance by +3.5% mIoU and +5.1% mAP. These results demonstrate that efficient, promptable segmentation is feasible directly on-camera, enabling privacy-preserving vision without cloud or host processing.
title PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.18807