相关论文: Matte Anything: Interactive Natural Image Matting …

Image deocclusion (or amodal completion) aims to recover the invisible regions (\ie, shape and appearance) of occluded instances in images. Despite recent advances, the scarcity of high-quality data that balances diversity, plausibility,…

In this paper we propose a global optimization-based approach to jointly matching a set of images. The estimated correspondences simultaneously maximize pairwise feature affinities and cycle consistency across multiple images. Unlike…

In this paper, we propose a way of synthesizing realistic images directly with natural language description, which has many useful applications, e.g. intelligent image manipulation. We attempt to accomplish such synthesis: given a source…

Accurately identifying and representing object edges is a challenging task in computer vision and image processing. The Segment Anything Model (SAM) has significantly influenced the field of image segmentation, but suffers from high memory…

Large web-sourced multimodal datasets have powered a slew of new methods for learning general-purpose visual representations, advancing the state of the art in computer vision and revolutionizing zero- and few-shot recognition. One crucial…

Unconstrained Image generation with high realism is now possible using recent Generative Adversarial Networks (GANs). However, it is quite challenging to generate images with a given set of attributes. Recent methods use style-based GAN…

Automatic photo adjustment is to mimic the photo retouching style of professional photographers and automatically adjust photos to the learned style. There have been many attempts to model the tone and the color adjustment globally with…

Generative models such as StyleGAN2 and Stable Diffusion have achieved state-of-the-art performance in computer vision tasks such as image synthesis, inpainting, and de-noising. However, current generative models for face inpainting often…

Transparency-aware generation requires modeling not only RGB appearance but also alpha-based opacity and cross-layer composition, which are essential for tasks such as image matting, object removal, layer decomposition, and multi-layer…

Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods. To this end, we introduce an…

In computed tomography imaging, metal implants frequently generate severe artifacts that compromise image quality and hinder diagnostic accuracy. There are three main challenges in the existing methods: the deterioration of organ and tissue…

In this work, we propose an AI-based technique using freely available satellite images like Landsat and Sentinel to create natural features over OSM in congruence with human editors acting as initiators and validators. The method is based…

Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting…

Mask-guided matting networks have achieved significant improvements and have shown great potential in practical applications in recent years. However, simply learning matting representation from synthetic and lack-of-real-world-diversity…

Co-salient object detection, with the target of detecting co-existed salient objects among a group of images, is gaining popularity. Recent works use the attention mechanism or extra information to aggregate common co-salient features,…

In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In…

Semantic image inpainting is a challenging task where large missing regions have to be filled based on the available visual data. Existing methods which extract information from only a single image generally produce unsatisfactory results…

Detecting transparent objects in natural scenes is challenging due to the low contrast in texture, brightness and colors. Recent deep-learning-based works reveal that it is effective to leverage boundaries for transparent object detection…

This paper presents LatentPatch, a new method for generating realistic images from a small dataset of only a few images. We use a lightweight model with only a few thousand parameters. Unlike traditional few-shot generation methods that…

How does one adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification? Inspired by prompting in NLP, this paper investigates visual prompting: given input-output image example(s)…