Related papers: MERIT: Multi-domain Efficient RAW Image Translatio…
Effective environment perception is crucial for enabling downstream robotic applications. Individual robotic agents often face occlusion and limited visibility issues, whereas multi-agent systems can offer a more comprehensive mapping of…
Medical vision-language models show strong potential for joint reasoning over medical images and clinical text, but their performance often degrades under domain shift caused by variations in imaging devices, acquisition protocols, and…
In the computer vision community, the preference for pre-training visual models has largely shifted toward sRGB images due to their ease of acquisition and compact storage. However, camera RAW images preserve abundant physical details…
In resource-constrained environments, one can employ spatial multiplexing cameras to acquire a small number of measurements of a scene, and perform effective reconstruction or high-level inference using purely data-driven neural networks.…
sRGB images are now the predominant choice for pre-training visual models in computer vision research, owing to their ease of acquisition and efficient storage. Meanwhile, the advantage of RAW images lies in their rich physical information…
3D LiDAR sensors are indispensable for the robust vision of autonomous mobile robots. However, deploying LiDAR-based perception algorithms often fails due to a domain gap from the training environment, such as inconsistent angular…
Camera sensor RAW data offers intrinsic advantages for object detection, including deeper bit depth, preserved physical information, and freedom from image signal processor (ISP) distortions. However, varying exposure conditions, spectral…
Images captured in challenging environments often experience various forms of degradation, including noise, color cast, blur, and light scattering. These effects significantly reduce image quality, hindering their applicability in…
A novel framework to construct an efficient sensing (measurement) matrix, called mixed adaptive-random (MAR) matrix, is introduced for directly acquiring a compressed image representation. The mixed sampling (sensing) procedure hybridizes…
Neural Radiance Field (NeRF) has revolutionized novel-view rendering tasks and achieved impressive results. However, the inefficient sampling and per-scene optimization hinder its wide applications. Though some generalizable NeRFs have been…
Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain…
In the last few years, unpaired image-to-image translation has witnessed remarkable progress. Although the latest methods are able to generate realistic images, they crucially rely on a large number of labeled images. Recently, some methods…
Foundation models like ChatGPT and Sora that are trained on a huge scale of data have made a revolutionary social impact. However, it is extremely challenging for sensors in many different fields to collect similar scales of natural images…
Image translation is a burgeoning field in computer vision where the goal is to learn the mapping between an input image and an output image. However, most recent methods require multiple generators for modeling different domain mappings,…
Composed Image Retrieval (CIR) uses a reference image and a modification text as a query to retrieve a target image satisfying the requirement of ``modifying the reference image according to the text instructions''. However, existing CIR…
Plant health can be monitored dynamically using multispectral sensors that measure Near-Infrared reflectance (NIR). Despite this potential, obtaining and annotating high-resolution NIR images poses a significant challenge for training deep…
Accurate measurement of spatially variant noise in dynamic magnetic resonance (MR) images acquired using parallel imaging methods is problematic. We propose a new method based on the random matrix theory to accurately assess the noise…
Machine learning and computer vision methods are showing good performance in medical imagery analysis. Yetonly a few applications are now in clinical use and one of the reasons for that is poor transferability of themodels to data from…
Modern multi-object tracking (MOT) systems usually model the trajectories by associating per-frame detections. However, when camera motion, fast motion, and occlusion challenges occur, it is difficult to ensure long-range tracking or even…
Images can vary according to changes in viewpoint, resolution, noise, and illumination. In this paper, we aim to learn representations for an image, which are robust to wide changes in such environmental conditions, using training pairs of…