Related papers: Hierarchical and Progressive Image Matting
RGB-D saliency detection aims to fuse multi-modal cues to accurately localize salient regions. Existing works often adopt attention modules for feature modeling, with few methods explicitly leveraging fine-grained details to merge with…
Portrait harmonization aims to composite a subject into a new background, adjusting its lighting and color to ensure harmony with the background scene. Existing harmonization techniques often only focus on adjusting the global color and…
Multi-exposure High Dynamic Range (HDR) imaging is a challenging task when facing truncated texture and complex motion. Existing deep learning-based methods have achieved great success by either following the alignment and fusion pipeline…
The captured images under low light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task,…
Learning to dehaze single hazy images, especially using a small training dataset is quite challenging. We propose a novel generative adversarial network architecture for this problem, namely back projected pyramid network (BPPNet), that…
We propose a method for creating a matte -- the per-pixel foreground color and alpha -- of a person by taking photos or videos in an everyday setting with a handheld camera. Most existing matting methods require a green screen background or…
We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…
Natural image matting algorithms aim to predict the transparency map (alpha-matte) with the trimap guidance. However, the production of trimap often requires significant labor, which limits the widespread application of matting algorithms…
A number of psychological and physiological evidences suggest that early visual attention works in a coarse-to-fine way, which lays a basis for the reverse hierarchy theory (RHT). This theory states that attention propagates from the top…
Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each…
Benefiting from the developments in deep learning technology, deep-learning-based algorithms employing automatic feature extraction have achieved remarkable performance on the change detection (CD) task. However, the performance of existing…
Natural image matting is a fundamental problem in computational photography and computer vision. Deep neural networks have seen the surge of successful methods in natural image matting in recent years. In contrast to traditional…
We present a novel approach of color transfer between images by exploring their high-level semantic information. First, we set up a database which consists of the collection of downloaded images from the internet, which are segmented…
Mapping Low Dynamic Range (LDR) images with different exposures to High Dynamic Range (HDR) remains nontrivial and challenging on dynamic scenes due to ghosting caused by object motion or camera jitting. With the success of Deep Neural…
Image harmonization aims at adjusting the appearance of the foreground to make it more compatible with the background. Without exploring background illumination and its effects on the foreground elements, existing works are incapable of…
Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly used in daytime…
Fine-grained visual classification aims to recognize images belonging to multiple sub-categories within a same category. It is a challenging task due to the inherently subtle variations among highly-confused categories. Most existing…
Real-time understanding of continuous video streams is essential for intelligent agents operating in high-stakes environments, including autonomous vehicles, surveillance drones, and disaster response robots. Yet, most existing video…
Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised…
Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…