Related papers: Fast and Adjustable Resolution Grazing Incidence x…
Diffusion models are the current state-of-the-art for solving inverse problems in imaging. Their impressive generative capability allows them to approximate sampling from a prior distribution, which alongside a known likelihood function…
Recent advancements in 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have achieved impressive results in real-time 3D reconstruction and novel view synthesis. However, these methods struggle in large-scale, unconstrained…
Lidar point cloud distortion from moving object is an important problem in autonomous driving, and recently becomes even more demanding with the emerging of newer lidars, which feature back-and-forth scanning patterns. Accurately estimating…
Diffusion models recently have been successfully applied for the visual synthesis of strikingly realistic appearing images. This raises strong concerns about their potential for malicious purposes. In this paper, we propose using the…
This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to effectively factorize the scene into material properties, light, and geometry. The key contributions lie in three-fold. We compute…
3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking. However, 3DGS fails to accurately represent surfaces due to the…
X-ray grating interferometry is an excellent technique for X-ray phase contrast imaging and X-ray wavefront sensing with applications in materials science, biology and medical diagnosis. Among other requirements, the method depends on the…
We present a concept of the X-ray imaging system with high angular-resolution and moderate sensitivity. In this concept, a two-dimensional detector, i.e., imager, is put at a slightly out-of-focused position of the focusing mirror, rather…
Grazing incidence mirrors for X-ray astronomy are usually designed in the parabola-hyperbola (Wolter I) configuration. This design allows for optimal images on-axis, which however degrade rapidly with the off-axis angle. Mirror surfaces…
We show the developments carried out to improve the silicon sensor technology for the detection of soft X-rays with hybrid X-ray detectors. An optimization of the entrance window technology is required to improve the quantum efficiency. The…
Fringe projection profilometry-based 3-D reconstruction of objects with high reflectivity and low surface roughness remains a significant challenge. When measuring such glossy surfaces, specular reflection and indirect illumination often…
Feedforward 3D Gaussian Splatting (3DGS) often struggles in trajectory-based sparse-view driving scenes. Existing Gaussian repair methods mainly target optimization-based 3DGS, while diffusion-based repair is typically restricted to…
Instance-level change detection in 3D scenes presents significant challenges, particularly in uncontrolled environments lacking labeled image pairs, consistent camera poses, or uniform lighting conditions. This paper addresses these…
Purpose: Handheld gamma cameras with coded aperture collimators are under investigation for intraoperative imaging in nuclear medicine. Coded apertures are a promising collimation technique for applications such as lymph node localization…
We propose LiRaFusion to tackle LiDAR-radar fusion for 3D object detection to fill the performance gap of existing LiDAR-radar detectors. To improve the feature extraction capabilities from these two modalities, we design an early fusion…
Deep learning methods for accelerated MRI achieve state-of-the-art results but largely ignore additional speedups possible with noncartesian sampling trajectories. To address this gap, we created a generative diffusion model-based…
Inverse rendering of glossy objects from RGB imagery remains fundamentally limited by inherent ambiguity. Although NeRF-based methods achieve high-fidelity reconstruction via dense-ray sampling, their computational cost is prohibitive.…
Recovering the intrinsic physical attributes of a scene from images, generally termed as the inverse rendering problem, has been a central and challenging task in computer vision and computer graphics. In this paper, we present GUS-IR, a…
Diffusion/score-based models have recently emerged as powerful generative priors for solving inverse problems, including accelerated MRI reconstruction. While their flexibility allows decoupling the measurement model from the learned prior,…
Diffraction-limited focusing deep into biological tissue is challenging due to spherical aberrations that lead to a broadening of the focal spot particularly in axial direction. While the diffraction-limit can be restored employing…