Related papers: ViViD++: Vision for Visibility Dataset
With the rapid advancement of generative models, highly realistic image synthesis has posed new challenges to digital security and media credibility. Although AI-generated image detection methods have partially addressed these concerns, a…
The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed…
Recently, by using deep neural network based algorithms, object classification, detection and semantic segmentation solutions are significantly improved. However, one challenge for 2D image-based systems is that they cannot provide accurate…
In this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset. The proposed benchmark provides drastic appearance variations…
Effectively localizing an agent in a realistic, noisy setting is crucial for many embodied vision tasks. Visual Odometry (VO) is a practical substitute for unreliable GPS and compass sensors, especially in indoor environments. While…
Event cameras are bio-inspired sensors that differ from conventional frame cameras: Instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes, and output a stream of events that encode the time,…
The physical and textural attributes of objects have been widely studied for recognition, detection and segmentation tasks in computer vision.~A number of datasets, such as large scale ImageNet, have been proposed for feature learning using…
Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…
Robust Visual SLAM (vSLAM) is essential for autonomous systems operating in real-world environments, where challenges such as dynamic objects, low texture, and critically, varying illumination conditions often degrade performance. Existing…
Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environments. To achieve this, we are exploring and evaluating a…
Long-duration, off-road, autonomous missions require robots to continuously perceive their surroundings regardless of the ambient lighting conditions. Most existing autonomy systems heavily rely on active sensing, e.g., LiDAR, RADAR, and…
The assumption of scene rigidity is common in visual SLAM algorithms. However, it limits their applicability in populated real-world environments. Furthermore, most scenarios including autonomous driving, multi-robot collaboration and…
Implicit neural SLAM has achieved remarkable progress recently. Nevertheless, existing methods face significant challenges in non-ideal scenarios, such as motion blur or lighting variation, which often leads to issues like convergence…
The traditional visual-inertial SLAM system often struggles with stability under low-light or motion-blur conditions, leading to potential lost of trajectory tracking. High accuracy and robustness are essential for the long-term and stable…
Existing object detection methods often consider sRGB input, which was compressed from RAW data using ISP originally designed for visualization. However, such compression might lose crucial information for detection, especially under…
Multi-view capture systems are complex systems to engineer. They require technical knowledge to install and intricate processes to setup related mainly to the sensors' spatial alignment (i.e. external calibration). However, with the ongoing…
This paper addresses the limitations of current datasets for 3D vision tasks in terms of accuracy, size, realism, and suitable imaging modalities for photometrically challenging objects. We propose a novel annotation and acquisition…
The rapid development of inexpensive commodity depth sensors has made keypoint detection and matching in the depth image modality an important problem in computer vision. Despite great improvements in recent RGB local feature learning…
Low-light is an inescapable element of our daily surroundings that greatly affects the efficiency of our vision. Research works on low-light has seen a steady growth, particularly in the field of image enhancement, but there is still a lack…
Non-uniform and multi-illuminant color constancy are important tasks, the solution of which will allow to discard information about lighting conditions in the image. Non-uniform illumination and shadows distort colors of real-world objects…