Related papers: Simulated recovery of LEO objects using sCMOS blin…
Within the field of robotics, computer vision remains a significant barrier to progress, with many tasks hindered by inefficient vision systems. This research proposes a generalized vision module leveraging YOLOv9, a state-of-the-art…
It is widely accepted that optimization of imaging system performance should be guided by task-based measures of image quality (IQ). It has been advocated that imaging hardware or data-acquisition designs should be optimized by use of an…
Detailed detector simulation and reconstruction of physics objects at the LHC are very CPU intensive and hence time consuming due to the high energy and multiplicity of the Monte-Carlo events and the complexity of the detectors. We present…
Real-time object detection in AR/VR systems faces critical computational constraints, requiring sub-10\,ms latency within tight power budgets. Inspired by biological foveal vision, we propose a two-stage pipeline that combines…
MIMO (multiple input, multiple output) approaches are a recent trend in neural network architectures for video restoration problems, where each network evaluation produces multiple output frames. The video is split into non-overlapping…
Earth Observation (EO) has traditionally involved the transmission of a large volume of raw data to map the Earth surface. This results in congestion to the satellite network and delays in the availability of the results, invalidating the…
State-of-the-art methods in generative representation learning yield semantic disentanglement, but typically do not consider physical scene parameters, such as geometry, albedo, lighting, or camera. We posit that inverse rendering, a way to…
We consider the problem of recovering elements of a low-dimensional model from linear measurements. From signal and image processing to inverse problems in data science, this question has been at the center of many applications. Lately,…
We consider blind ptychography, an imaging technique which aims to reconstruct an object of interest from a set of its diffraction patterns, each obtained by a local illumination. As the distribution of the light within the illuminated…
Imaging reconstruction of interferometric data is a hard ill-posed inverse problem. Its difficulty is increased when observing the Galactic Center, which is obscured by a scattering screen. This is because the scattering breaks the…
The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty estimation methods…
Semi-supervised video object segmentation (VOS) has been largely driven by space-time memory (STM) networks, which store past frame features in a spatiotemporal memory to segment the current frame via softmax attention. However, STM…
This paper presents a method of reconstructing full-body locomotion sequences for virtual characters in real-time, using data from a single inertial measurement unit (IMU). This process can be characterized by its difficulty because of the…
We present a pipeline for searching for trans-Neptunian objects (TNOs) using data from the TESS mission, that includes a novel optimization-based framework for subtracting the effects of scattered light and pointing jitter. The background…
Multi-object tracking (MOT) is a challenging practical problem for vision based applications. Most recent approaches for MOT use precomputed detections from models such as Faster RCNN, performing fine-tuning of bounding boxes and…
The emergence of optical interferometers with three and more telescopes allows image reconstruction of astronomical objects at the milliarcsecond scale. However, some objects contain components with very different spectral energy…
Recent works have demonstrated non-line of sight (NLOS) reconstruction by using the time-resolved signal frommultiply scattered light. These works combine ultrafast imaging systems with computation, which back-projects the recorded…
Stereo vision techniques have been widely used in civil engineering to acquire 3-D road data. The two important factors of stereo vision are accuracy and speed. However, it is very challenging to achieve both of them simultaneously and…
3D object detection based on monocular camera data is a key enabler for autonomous driving. The task however, is ill-posed due to lack of depth information in 2D images. Recent deep learning methods show promising results to recover depth…
We address the problem of unsupervised learning of complex articulated object models from 3D range data. We describe an algorithm whose input is a set of meshes corresponding to different configurations of an articulated object. The…