Related papers: DeS3: Adaptive Attention-driven Self and Soft Shad…

Recent advances in DUSt3R have enabled robust estimation of dense point clouds and camera parameters of static scenes, leveraging Transformer network architectures and direct supervision on large-scale 3D datasets. In contrast, the limited…

Self-supervised learning methods based on image patch reconstruction have witnessed great success in training auto-encoders, whose pre-trained weights can be transferred to fine-tune other downstream tasks of image understanding. However,…

Vision transformers (ViT) have demonstrated impressive performance across various machine vision problems. These models are based on multi-head self-attention mechanisms that can flexibly attend to a sequence of image patches to encode…

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a…

Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…

We propose Diff-Shadow, a global-guided diffusion model for shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover…

Shadows are common aspect of images and when left undetected can hinder scene understanding and visual processing. We propose a simple yet effective approach based on reflectance to detect shadows from single image. An image is first…

Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the variant, Local Vision Transformer, makes further improvements. The major component in Local Vision Transformer, local attention, performs the…

Person re-identification (ReID) under occlusions is a challenging problem in video surveillance. Most of existing person ReID methods take advantage of local features to deal with occlusions. However, these methods usually independently…

Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training data. However, this way of adversarial injection inevitably…

Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…

Person re-identification (ReID) models are known to suffer from camera bias, where learned representations cluster according to camera viewpoints rather than identity, leading to significant performance degradation under (inter-camera)…

The requirement for paired shadow and shadow-free images limits the size and diversity of shadow removal datasets and hinders the possibility of training large-scale, robust shadow removal algorithms. We propose a shadow removal method that…

Recently, transformer-based methods have shown exceptional performance in monocular 3D object detection, which can predict 3D attributes from a single 2D image. These methods typically use visual and depth representations to generate query…

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure for the subsequent HSI applications. Unfortunately, though witnessing the development of deep learning in HSI denoising area, existing convolution-based methods face…

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

Current shadow detection methods perform poorly when detecting shadow regions that are small, unclear or have blurry edges. In this work, we attempt to address this problem on two fronts. First, we propose a Fine Context-aware Shadow…

In this paper, we propose a 2-stage low-light image enhancement method called Self-Reference Deep Adaptive Curve Estimation (Self-DACE). In the first stage, we present an intuitive, lightweight, fast, and unsupervised luminance enhancement…

Shadows can originate from occlusions in both direct and indirect illumination. Although most current shadow removal research focuses on shadows caused by direct illumination, shadows from indirect illumination are often just as pervasive,…