Related papers: RobuSTereo: Robust Zero-Shot Stereo Matching under…

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…

Purpose: Stereo matching methods that enable depth estimation are crucial for visualization enhancement applications in computer-assisted surgery (CAS). Learning-based stereo matching methods are promising to predict accurate results on…

While perspective is a well-studied topic in art, it is generally taken for granted in images. However, for the recent wave of high-quality image synthesis methods such as latent diffusion models, perspective accuracy is not an explicit…

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…

We present DiffIR2VR-Zero, a zero-shot framework that enables any pre-trained image restoration diffusion model to perform high-quality video restoration without additional training. While image diffusion models have shown remarkable…

Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional image enhancement techniques almost impossible to apply. Very…

We present a novel method for scene change detection that leverages the robust feature extraction capabilities of a visual foundational model, DINOv2, and integrates full-image cross-attention to address key challenges such as varying…

Current methods for restoring underexposed images typically rely on supervised learning with paired underexposed and well-illuminated images. However, collecting such datasets is often impractical in real-world scenarios. Moreover, these…

Achieving robust and accurate spatial perception under adverse weather and lighting conditions is crucial for the high-level autonomy of self-driving vehicles and robots. However, existing perception algorithms relying on the visible…

In this thesis, we leverage monocular cameras on aerial robots to predict depth and semantic maps in low-altitude unstructured environments. We propose a joint deep-learning architecture, named Co-SemDepth, that can perform the two tasks…

Stereo matching is a significant part in many computer vision tasks and driving-based applications. Recently cost volume-based methods have achieved great success benefiting from the rich geometry information in paired images. However, the…

We present an improved three-step pipeline for the stereo matching problem and introduce multiple novelties at each stage. We propose a new highway network architecture for computing the matching cost at each possible disparity, based on…

Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on image content-related features instead of overfitting…

We presented a method for improving computer vision tasks on images affected by adverse weather conditions, including distortions caused by adherent raindrops. Overcoming the challenge of applying computer vision to images affected by…

Photometric stereo is a technique aimed at determining surface normals through the utilization of shading cues derived from images taken under different lighting conditions. However, existing learning-based approaches often fail to…

In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems. Due to the lack of ground truth, our method is fully self-supervised, yet it produces precise depth with a subpixel precision of $1/30th$…

Recent learning-based visual localization methods use global descriptors to disambiguate visually similar places, but existing approaches often derive these descriptors from geometric cues alone (e.g., covisibility graphs), limiting their…

Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requiring training on downstream data. Recent works have confirmed…

Complex degradations like noise, blur, and low resolution are typical challenges in real world image fusion tasks, limiting the performance and practicality of existing methods. End to end neural network based approaches are generally…

Pooling heterogeneous datasets across domains is a common strategy in representation learning, but naive pooling can amplify distributional asymmetries and yield biased estimators, especially in settings where zero-shot generalization is…