UG2+ Challenge

Bridging the Gap Between Computational Photography and Visual Recognition:

7^th UG²+ Prize Challenge

CVPR 2024

The rapid development of computer vision algorithms increasingly allows automatic visual recognition to be incorporated into a suite of emerging applications. Some of these applications have less-than-ideal circumstances such as low-visibility environments, causing image captures to have degradations. In other more extreme applications, such as imagers for flexible wearables, smart clothing sensors, ultra-thin headset cameras, implantable in vivo imaging, and others, standard camera systems cannot even be deployed, requiring new types of imaging devices. Computational photography addresses the concerns above by designing new computational techniques and incorporating them into the image capture and formation pipeline. This raises a set of new questions. For example, what is the current state-of-the-art for image restoration for images captured in non-ideal circumstances? How can inference be performed on novel kinds of computational photography devices?

Continuing the success of the 1^st (CVPR'18), 2^nd (CVPR'19), 3^rd (CVPR'20), 4^th (CVPR'21), 5^th (CVPR'22), and 6^th (CVPR'23) UG² Prize Challenge workshops, we provide its 7^th version for CVPR 2024. It will inherit the successful benchmark dataset, platform and evaluation tools used by the previous UG2 workshops, but will also look at brand new aspects of the overall problem, significantly augmenting its existing scope.

Original high-quality contributions are solicited on the following topics:

Novel algorithms for robust object detection, segmentation or recognition on outdoor mobility platforms (UAVs, gliders, autonomous cars, outdoor robots etc.), under real-world adverse conditions and image degradations (haze, rain, snow, hail, dust, underwater, low-illumination, low resolution, etc.)

Novel models and theories for explaining, quantifying, and optimizing the mutual influence between the low-level computational photography tasks and various high-level computer vision tasks, and for the underlying degradation and recovery processes, of real-world images going through complicated adverse visual conditions.

Novel evaluation methods and metrics for image restoration and enhancement algorithms, with a particular emphasis on no-reference metrics, since for most real outdoor images with adverse visual conditions it is hard to obtain any clean “ground truth” to compare with.

Challenge Categories

Winners

Keynote speakers

Available Challenges

What is the current state-of-the-art for image restoration for images captured in non-ideal circumstances? How can inference be performed on novel kinds of computational photography devices?

The UG²+ Challenge seeks to advance the analysis of "difficult" imagery by applying image restoration and enhancement algorithms to improve analysis performance. Participants are tasked with developing novel algorithms to improve the analysis of imagery captured under problematic conditions.

Object Detection in Haze

While most current vision systems are designed to perform in environments where the subjects are well observable without (significant) attenuation or alteration, a dependable vision system must reckon with the entire spectrum of complex unconstrained and dynamic degraded outdoor environments. It is highly desirable to study to what extent, and in what sense, such challenging visual conditions can be coped with, for the goal of achieving robust visual sensing.

Our challenge is based on the A2I2-Haze, the first real haze dataset with in-situ smoke measurement aligned to aerial and ground imagery.

Atmospheric Turbulence Mitigation

The theories of turbulence and propagation of light through random media have been studied for the better part of a century. Yet progress for associated image reconstruction algorithms has been slow, as the turbulence mitigation problem has not thoroughly been given the modern treatments of advanced image processing approaches (e.g., deep learning methods) that have positively impacted a wide variety of other imaging domains (e.g., classification).

This challenge aims to promote the development of new image reconstruction algorithms for incoherent imaging through anisoplanatic turbulence.

All weather semantic segmentation

Images captured in adverse weather conditions significantly impact the performance of many vision tasks. Common weather phenomenon, including but not limited to rain, snow, fog, introduce visual degradations to captured images and videos. These degradations may include partial to severe occlusions of objects, illumination changes, noise, etc. As most vision algorithms assume clear weather, with no interference of particles present under adverse weather, their performance suffers due to the domain gap.

This challenge aims to spark the development of novel semantic segmentation algorithms for images captured under adverse weather conditions.

3D Smoky Reconstruction

Computer vision in low visibility is a problem that faces many challenges and remains largely open. Amplitude scattering provides a unique challenge in visibility because of the amount of ambient light present in the scene which is depth-dependent. In the case of self-driving cars or commercial UAVs, the ability of an optical system to see “through” the haze or fog present in real-world imaging is critical for making decisions which have significant impact on safety.

This challenge aims to promote development of accurate and efficient 3D reconstructions in the presence of amplitude scattering.

UAV Tracking and Pose Estimation

Recently, UAVs have become a major concern in frontline combat, contraband smuggling, and the endangerment of commercial aircraft, among other areas. Due to their compact size and quiet electric motors, they are difficult to detect by soldiers, law-enforcement and vehicles.

This challenge is positioned to play a pivotal role in advancing UAV threat detection, classification, trajectory estimation capabilities, and more.