Related papers: Semantic-guided Multi-Mask Image Harmonization
Semantic image synthesis (SIS) aims to generate realistic images that match given semantic masks. Despite recent advances allowing high-quality results and precise spatial control, they require a massive semantic segmentation dataset for…
Depth maps are used in a wide range of applications from 3D rendering to 2D image effects such as Bokeh. However, those predicted by single image depth estimation (SIDE) models often fail to capture isolated holes in objects and/or have…
In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information. Recent development in deep generative models enables an efficient end-to-end framework for image…
Real-world image matting is essential for applications in content creation and augmented reality. However, it remains challenging due to the complex nature of scenes and the scarcity of high-quality datasets. To address these limitations,…
Modern camera pipelines apply extensive on-device processing, such as exposure adjustment, white balance, and color correction, which, while beneficial individually, often introduce photometric inconsistencies across views. These appearance…
Many image processing tasks can be formulated as translating images between two image domains, such as colorization, super resolution and conditional image synthesis. In most of these tasks, an input image may correspond to multiple…
Editing High Dynamic Range (HDR) environment maps using an inverse differentiable rendering architecture is a complex inverse problem due to the sparsity of relevant pixels and the challenges in balancing light sources and background. The…
Facial image manipulation has achieved great progress in recent years. However, previous methods either operate on a predefined set of face attributes or leave users little freedom to interactively manipulate images. To overcome these…
Given a composite image, image harmonization aims to adjust the foreground illumination to be consistent with background. Previous methods have explored transforming foreground features to achieve competitive performance. In this work, we…
This paper investigates the problem of reconstructing hyperspectral (HS) images from single RGB images captured by commercial cameras, \textbf{without} using paired HS and RGB images during training. To tackle this challenge, we propose a…
Deep learning-based methods for low-light image enhancement typically require enormous paired training data, which are impractical to capture in real-world scenarios. Recently, unsupervised approaches have been explored to eliminate the…
Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique. The existing MIM methods adopt the strategy to mask random patches of the image and reconstruct the…
Sparse hyperspectral unmixing from large spectral libraries has been considered to circumvent limitations of endmember extraction algorithms in many applications. This strategy often leads to ill-posed inverse problems, which can benefit…
Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects…
Image fusion methods and metrics for their evaluation have conventionally used pixel-based or low-level features. However, for many applications, the aim of image fusion is to effectively combine the semantic content of the input images.…
Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and style between inpainted regions and the surrounding background.…
Foundation models have recently gained tremendous popularity in medical image analysis. State-of-the-art methods leverage either paired image-text data via vision-language pre-training or unpaired image data via self-supervised pre-training…
Semi-supervised semantic segmentation aims to utilize limited labeled images and abundant unlabeled images to achieve label-efficient learning, wherein the weak-to-strong consistency regularization framework, popularized by FixMatch, is…
Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus…
Automatic estimation of 3D human pose from monocular RGB images is a challenging and unsolved problem in computer vision. In a supervised manner, approaches heavily rely on laborious annotations and present hampered generalization ability…