Real-World Computer Vision from Inputs with Limited Quality (RLQ)

How is the robustness of the current state-of-the-art for recognition and detection algorithms in non-ideal visual environments? While the visual recognition research has made tremendous progress in recent years, most models are trained, applied, and evaluated on high-quality (HQ) visual data. However, in many emerging applications such as robotics and autonomous driving, the performances of visual sensing and analytics are largely jeopardized by low-quality(LQ) visual data acquired from unconstrained environments, suffering from various types of degradation such as low resolution, noise, occlusion, motion blur, contrast, brightness, sharpness, out-of-focus etc. We are organizing the 2nd RLQ workshop in conjunction with ECCV 2020 to provide an integrated forum for both low-level and high-level vision researchers to review the recent progress of robust recognition models from LQ visual data and the novel image restoration algorithms. You could contribute to our workshop in three aspects:

[1. Paper Submission] Researchers are encouraged to submit either full-paper (4-page including reference to 14-page plus reference)or half-baked abstract (4-page including reference) to our workshop.

[2. TOD Challenge] In conjunction with the workshop, we will hold the 1st Tiny Object Detection (TOD) Challenge. This challenge targets at establishing a baseline for tiny person detection by presenting a new benchmark and various approaches, opening up a promising direction for tiny object detection in the wild. The new benchmark, named TinyPerson, spans challenges including extreme low-resolution, background diversity, multi-objects, part-invisibility, and various complex backgrounds that are far beyond those in existing datasets.

[3. UDC Challenge] We will also hold the first image restoration challenge on Under-Display Camera (UDC). The new trend of full-screen devices encourages us to position a camera behind a screen. Removing the bezel and centralizing the camera under the screen brings larger display-to-body ratio and enhances eye contact in video chat, but also causes image degradation. we focus on a newly-defined Under-Display Camera (UDC), as a novel real-world single image restoration problem. We will release the UDC dataset for training and testing, and rank the algorithms according to the image recovery performance.

For the participants of the challenge, prize and possible internship opportunities will be awarded. Top-ranked authors will be invited to co-author the challenge report and contribute another workshop paper describing the outstanding algorithms.

For inquiry, please send emails to one of the following addresses:

• UDC Challenge: Yuqian Zhou zhouyuqian133@gmail.com
• TOD Challenge: Zhenjun Han hanzhj@ucas.ac.cn
• General Inquiry: Humphrey Shi shihonghui3@gmail.com