Towards Reflected Object Detection: A Benchmark

TL;DR

This paper introduces RODD, a comprehensive benchmark dataset for reflected object detection, highlighting the challenges and providing baseline results to foster future research in this underexplored area.

Contribution

The paper presents RODD, a new large-scale dataset for reflected object detection, and evaluates existing models, revealing their limitations and the need for specialized approaches.

Findings

Existing models perform poorly on reflected objects.

RODD contains over 21,000 images with annotations.

Reflected object detection remains a challenging task.

Abstract

Object detection has greatly improved over the past decade thanks to advances in deep learning and large-scale datasets. However, detecting objects reflected in surfaces remains an underexplored area. Reflective surfaces are ubiquitous in daily life, appearing in homes, offices, public spaces, and natural environments. Accurate detection and interpretation of reflected objects are essential for various applications. This paper addresses this gap by introducing a extensive benchmark specifically designed for Reflected Object Detection. Our Reflected Object Detection Dataset (RODD) features a diverse collection of images showcasing reflected objects in various contexts, providing standard annotations for both real and reflected objects. This distinguishes it from traditional object detection benchmarks. RODD encompasses 10 categories and includes 21,059 images of real and reflected objects across different backgrounds, complete with standard bounding box annotations and the classification of objects as real or reflected. Additionally, we present baseline results by adapting five state-of-the-art object detection models to address this challenging task. Experimental results underscore the limitations of existing methods when applied to reflected object detection, highlighting the need for specialized approaches. By releasing RODD, we aim to support and advance future research on detecting reflected objects. Dataset and code are available at: https://github.com/jirouvan/ROD.