ROI-Packing: Efficient Region-Based Compression for Machine Vision

2025/12/10 by Eimon, Md Eimran Hossain, Krause, Alena, Perera, Ashan +4 · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2512.09258

Abstract

This paper introduces ROI-Packing, an efficient image compression method tailored specifically for machine vision. By prioritizing regions of interest (ROI) critical to end-task accuracy and packing them efficiently while discarding less relevant data, ROI-Packing achieves significant compression efficiency without requiring retraining or fine-tuning of end-task models. Comprehensive evaluations across five datasets and two popular tasks-object detection and instance segmentation-demonstrate up to a 44.10% reduction in bitrate without compromising end-task accuracy, along with an 8.88 % improvement in accuracy at the same bitrate compared to the state-of-the-art Versatile Video Coding (VVC) codec standardized by the Moving Picture Experts Group (MPEG).

Citations

• YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
• Large-scale interactive object segmentation with human annotators
• Mask R-CNN
• Feature Pyramid Networks for Object Detection
• Aggregated Residual Transformations for Deep Neural Networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Worst-Case Performance Bounds for Simple One-Dimensional Packing Algorithms

Cited by

• Emerging Standards for Machine-to-Machine Video Coding

Related

• Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics
• SLIM: Semantic-based Low-bitrate Image compression for Machines by leveraging diffusion
• VVC+M: Plug and Play Scalable Image Coding for Humans and Machines
• Learned Image Compression for Machine Perception
• CompressAI-Vision: Open-source software to evaluate compression methods for computer vision tasks