Related papers: Optimized Visibility Functions for Revectorization…
Video synthetic aperture radar (ViSAR) has attracted substantial attention in the moving target detection (MTD) field due to its ability to continuously monitor changes in the target area. In ViSAR, the moving targets' shadows will not…
Modeling strong gravitational lenses in order to quantify the distortions in the images of background sources and to reconstruct the mass density in the foreground lenses has been a difficult computational challenge. As the quality of…
We study the energy minimization problem in low-level vision tasks from a novel perspective. We replace the heuristic regularization term with a learnable subspace constraint, and preserve the data term to exploit domain knowledge derived…
Color names based image representation is successfully used in person re-identification, due to the advantages of being compact, intuitively understandable as well as being robust to photometric variance. However, there exists the diversity…
When adapting Simultaneous Mapping and Localization (SLAM) to real-world applications, such as autonomous vehicles, drones, and augmented reality devices, its memory footprint and computing cost are the two main factors limiting the…
We have developed a new technique called Direct Shear Mapping (DSM) to measure gravitational lensing shear directly from observations of a single background source. The technique assumes the velocity map of an un-lensed, stably-rotating…
We consider robust submodular maximization problems (RSMs), where given a set of $m$ monotone submodular objective functions, the robustness is with respect to the worst-case (scaled) objective function. The model we consider generalizes…
The performance of robotic imitation learning is fundamentally limited by data quality and training strategies. Prevalent sampling strategies on RLBench suffer from severe keyframe redundancy and imbalanced temporal distribution, leading to…
Incrementally recovering real-sized 3D geometry from a pose-free RGB stream is a challenging task in 3D reconstruction, requiring minimal assumptions on input data. Existing methods can be broadly categorized into end-to-end and visual…
Visual SLAM has regained attention due to its ability to provide perceptual capabilities and simulation test data for Embodied AI. However, traditional SLAM methods struggle to meet the demands of high-quality scene reconstruction, and…
Most recently, tensor-SVD is implemented on multi-view self-representation clustering and has achieved the promising results in many real-world applications such as face clustering, scene clustering and generic object clustering. However,…
Existing shadow detection models struggle to differentiate dark image areas from shadows. In this paper, we tackle this issue by verifying that all detected shadows are real, i.e. they have paired shadow casters. We perform this step in a…
In this paper, we present a novel differentiable point-based rendering framework to achieve photo-realistic relighting. To make the reconstructed scene relightable, we enhance vanilla 3D Gaussians by associating extra properties, including…
Shadow removal is a task aimed at erasing regional shadows present in images and reinstating visually pleasing natural scenes with consistent illumination. While recent deep learning techniques have demonstrated impressive performance in…
Unlike many urban localization methods that return point-valued estimates, a set-valued representation enables robustness by ensuring that a continuum of possible positions obeys safety constraints. One strategy with the potential for…
(Abridged) Weak gravitational lensing is an ideal probe of the dark universe. In recent years, several linear methods have been developed to reconstruct the density distribution in the Universe in three dimensions, making use of photometric…
Jointly estimating camera poses and mapping scenes from RGBD images is a fundamental task in simultaneous localization and mapping (SLAM). State-of-the-art methods employ 3D Gaussians to represent a scene, and render these Gaussians through…
Robust SLAM is a crucial enabler for autonomous navigation in natural, semi-structured environments such as parks and gardens. However, these environments present unique challenges for SLAM due to frequent seasonal changes, varying light…
Creating relightable and animatable human avatars from monocular videos is a rising research topic with a range of applications, e.g. virtual reality, sports, and video games. Previous works utilize neural fields together with physically…
Composite function minimization captures a wide spectrum of applications in both computer vision and machine learning. It includes bound constrained optimization and cardinality regularized optimization as special cases. This paper proposes…