Related papers: RoSe: Robust Self-supervised Stereo Matching under…
This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…
Noise robustness is essential for deploying automatic speech recognition (ASR) systems in real-world environments. One way to reduce the effect of noise interference is to employ a preprocessing module that conducts speech enhancement, and…
Video stabilization plays a central role to improve videos quality. However, despite the substantial progress made by these methods, they were, mainly, tested under standard weather and lighting conditions, and may perform poorly under…
Most state-of-the-art semantic segmentation approaches only achieve high accuracy in good conditions. In practically-common but less-discussed adverse environmental conditions, their performance can decrease enormously. Existing studies…
Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address…
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.…
Lidar sensors are frequently used in environment perception for autonomous vehicles and mobile robotics to complement camera, radar, and ultrasonic sensors. Adverse weather conditions are significantly impacting the performance of…
Photometric stereo is a method for estimating the normal vectors of an object from images of the object under varying lighting conditions. Motivated by several recent works that extend photometric stereo to more general objects and lighting…
The deep convolutional neural network has achieved significant progress for single image rain streak removal. However, most of the data-driven learning methods are full-supervised or semi-supervised, unexpectedly suffering from significant…
Depth estimation, essential for autonomous driving, seeks to interpret the 3D environment surrounding vehicles. The development of radar sensors, known for their cost-efficiency and robustness, has spurred interest in radar-camera…
Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely unknown if the nature of the representations induced by the…
Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks. However, current RS approaches drastically decrease standard accuracy on unperturbed data, severely limiting…
Image super-resolution is an important research area in computer vision that has a wide variety of applications including surveillance, medical imaging etc. Real-world signal image super-resolution has become very popular now-a-days due to…
This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…
Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…
While recent low-cost radar-camera approaches have shown promising results in multi-modal 3D object detection, both sensors face challenges from environmental and intrinsic disturbances. Poor lighting or adverse weather conditions degrade…
Image restoration under multiple adverse weather conditions aims to develop a single model to recover the underlying scene with high visibility. Weather-related artifacts vary with the particle's distance to the camera according to the…
Image denoising has achieved unprecedented progress as great efforts have been made to exploit effective deep denoisers. To improve the denoising performance in realworld, two typical solutions are used in recent trends: devising better…
In this paper, we present a framework for computing dense keypoint correspondences between images under strong scene appearance changes. Traditional methods, based on nearest neighbour search in the feature descriptor space, perform poorly…
Reconstructing the 3D shape of an object using several images under different light sources is a very challenging task, especially when realistic assumptions such as light propagation and attenuation, perspective viewing geometry and…