Related papers: Panda: Self-distillation of Reusable Sensor-level …
Unified image restoration is a significantly challenging task in low-level vision. Existing methods either make tailored designs for specific tasks, limiting their generalizability across various types of degradation, or rely on training…
Scientific measurements are often bottlenecked by suboptimal conditions, whether that be noise, incomplete spatial coverage, or limited resolution, rendering accurate field reconstruction a difficult task. We introduce LatentPDE, a latent…
We present a data-driven, differentiable neural network model designed to learn the temperature field, its gradient, and the cooling rate, while implicitly representing the melt pool boundary as a level set in laser powder bed fusion. The…
Representation-based retrieval models, so-called bi-encoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current state-of-the-art bi-encoders are trained using an expensive…
Liquid Argon Time Projection Chambers (LArTPCs) are ideal detectors for precision neutrino physics. These detectors, when located deep underground, can also be used for measurements of proton decay, and astrophysical neutrinos. The…
In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or videos, using carefully…
Recently, perceptual image compression has achieved significant advancements, delivering high visual quality at low bitrates for natural images. However, for screen content, existing methods often produce noticeable artifacts when…
MicroBooNE is a liquid argon time projection chamber (LArTPC) neutrino experiment that is currently running in the Booster Neutrino Beam at Fermilab. LArTPC technology allows for high-resolution, three-dimensional representations of…
Camera and lidar are important sensor modalities for robotics in general and self-driving cars in particular. The sensors provide complementary information offering an opportunity for tight sensor-fusion. Surprisingly, lidar-only methods…
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important. However, most existing completion methods rely on large paired datasets for training, which is…
We have previously reported on the construction and successful operation of the novel double phase Liquid Argon Large Electron Multiplier Time Projection Chamber (LAr LEM-TPC). This detector concept provides a 3D-tracking and calorimetric…
Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained…
Neutrons are important final-state particles in neutrino interactions, yet they are not considered or reconstructed in most current neutrino LArTPC physics analyses. In this paper, we present a simulation-based proof-of-concept study of…
The PANDA experiment at the international accelerator Facility for Antiproton and Ion Research in Europe (FAIR), Darmstadt, Germany, will address fundamental questions of hadron physics using $\bar{p}p$ annihilations. Excellent Particle…
Subatomic particle track reconstruction (tracking) is a vital task in High-Energy Physics experiments. Tracking is exceptionally computationally challenging and fielded solutions, relying on traditional algorithms, do not scale linearly.…
Diffusion models, such as Stable Diffusion (SD), offer the ability to generate high-resolution images with diverse features, but they come at a significant computational and memory cost. In classifier-free guided diffusion models, prolonged…
As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for various downstream tasks, including those related to vision-based systems.…
A main bottleneck of learning-based robotic scene understanding methods is the heavy reliance on extensive annotated training data, which often limits their generalization ability. In LiDAR panoptic segmentation, this challenge becomes even…
The use of machine learning algorithms is an attractive way to produce very fast detector simulations for scattering reactions that can otherwise be computationally expensive. Here we develop a factorised approach where we deal with each…
Label assignment in object detection aims to assign targets, foreground or background, to sampled regions in an image. Unlike labeling for image classification, this problem is not well defined due to the object's bounding box. In this…