Related papers: Perceptual Loss for Robust Unsupervised Homography…
Homography estimation is an important task in computer vision applications, such as image stitching, video stabilization, and camera calibration. Traditional homography estimation methods heavily depend on the quantity and distribution of…
Self-supervised monocular depth estimation serves as a key task in the development of endoscopic navigation systems. However, performance degradation persists due to uneven illumination inherent in endoscopic images, particularly in…
Image dehazing is an important task in the field of computer vision, aiming at restoring clear and detail-rich visual content from haze-affected images. However, when dealing with complex scenes, existing methods often struggle to strike a…
This paper proposes a geometric interpretation of the angles and scales which the orientation- and scale-covariant feature detectors, e.g. SIFT, provide. Two new general constraints are derived on the scales and rotations which can be used…
We propose a neural inverse rendering approach that jointly reconstructs geometry, spatially varying reflectance, and lighting conditions from multi-view images captured under varying directional lighting. Unlike prior multi-view…
Monocular omnidirectional depth estimation is receiving considerable research attention due to its broad applications for sensing 360{\deg} surroundings. Existing approaches in this field suffer from limitations in recovering small object…
Multimodal imaging and correlative analysis typically require image alignment. Contrastive learning can generate representations of multimodal images, reducing the challenging task of multimodal image registration to a monomodal one.…
Images captured in harsh environments often exhibit blurred details, reduced contrast, and color distortion, which hinder feature detection and matching, thereby affecting the accuracy and robustness of homography estimation. While visual…
The following three factors restrict the application of existing low-light image enhancement methods: unpredictable brightness degradation and noise, inherent gap between metric-favorable and visual-friendly versions, and the limited paired…
The challenges of learning a robust 6D pose function lie in 1) severe occlusion and 2) systematic noises in depth images. Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance…
Depth estimation from a single underwater image is one of the most challenging problems and is highly ill-posed. Due to the absence of large generalized underwater depth datasets and the difficulty in obtaining ground truth depth-maps,…
We develop a new unsupervised symmetry learning method that starts with raw data and provides the minimal generator of an underlying Lie group of symmetries, together with a symmetry-equivariant representation of the data, which turns the…
SOM is a type of unsupervised learning where the goal is to discover some underlying structure of the data. In this paper, a new extraction method based on the main idea of Concurrent Self-Organizing Maps (CSOM), representing a…
We introduce a probabilistic approach to ptychographic reconstruction in computational imaging. Ptychography is an imaging method where the complex amplitude of an object is estimated from a sequence of diffraction measurements. We…
We present HUME, a simple model-agnostic framework for inferring human labeling of a given dataset without any external supervision. The key insight behind our approach is that classes defined by many human labelings are linearly separable…
This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…
Autoencoders are commonly trained using element-wise loss. However, element-wise loss disregards high-level structures in the image which can lead to embeddings that disregard them as well. A recent improvement to autoencoders that helps…
Depth estimation from a single image is an active research topic in computer vision. The most accurate approaches are based on fully supervised learning models, which rely on a large amount of dense and high-resolution (HR) ground-truth…
Monocular depth estimation is a critical task for autonomous driving and many other computer vision applications. While significant progress has been made in this field, the effects of viewpoint shifts on depth estimation models remain…
We present in this paper a new Bayesian semi-blind approach for foreground removal in observations of the 21-cm signal with interferometers. The technique, which we call HIEMICA (HI Expectation-Maximization Independent Component Analysis),…