BioDet: Boosting Industrial Object Detection with Image Preprocessing Strategies

TL;DR

BioDet introduces a plug-in pipeline that enhances industrial object detection by applying image preprocessing strategies like low-light enhancement and background removal, significantly improving accuracy under challenging conditions with minimal additional computational cost.

Contribution

The paper presents a standardized detection pipeline that integrates open-vocabulary foundation models and image preprocessing to reduce domain shift and false positives in industrial object detection.

Findings

Significant boost in detection accuracy on BOP benchmarks

Effective suppression of false positives from SAM outputs

Minimal inference overhead with improved robustness

Abstract

Accurate 6D pose estimation is essential for robotic manipulation in industrial environments. Existing pipelines typically rely on off-the-shelf object detectors followed by cropping and pose refinement, but their performance degrades under challenging conditions such as clutter, poor lighting, and complex backgrounds, making detection the critical bottleneck. In this work, we introduce a standardized and plug-in pipeline for 2D detection of unseen objects in industrial settings. Based on current SOTA baselines, our approach reduces domain shift and background artifacts through low-light image enhancement and background removal guided by open-vocabulary detection with foundation models. This design suppresses the false positives prevalent in raw SAM outputs, yielding more reliable detections for downstream pose estimation. Extensive experiments on real-world industrial bin-picking benchmarks from BOP demonstrate that our method significantly boosts detection accuracy while incurring negligible inference overhead, showing the effectiveness and practicality of the proposed method.