Related papers: Learning to Incorporate Structure Knowledge for Im…
Exploiting internal spatial geometric constraints of sparse LiDARs is beneficial to depth completion, however, has been not explored well. This paper proposes an efficient method to learn geometry-aware embedding, which encodes the local…
General deep learning-based methods for infrared and visible image fusion rely on the unsupervised mechanism for vital information retention by utilizing elaborately designed loss functions. However, the unsupervised mechanism depends on a…
Recent advances in deep generative models have shown promising potential in image inpanting, which refers to the task of predicting missing pixel values of an incomplete image using the known context. However, existing methods can be slow…
Existing image inpainting methods often produce artifacts when dealing with large holes in real applications. To address this challenge, we propose an iterative inpainting method with a feedback mechanism. Specifically, we introduce a deep…
Deep neural networks have shown promising results in image inpainting even if the missing area is relatively large. However, most of the existing inpainting networks introduce undesired artifacts and noise to the repaired regions. To solve…
In the image inpainting task, the ability to repair both high-frequency and low-frequency information in the missing regions has a substantial influence on the quality of the restored image. However, existing inpainting methods usually fail…
Recently, how to achieve precise image editing has attracted increasing attention, especially given the remarkable success of text-to-image generation models. To unify various spatial-aware image editing abilities into one framework, we…
Restoring reasonable and realistic content for arbitrary missing regions in images is an important yet challenging task. Although recent image inpainting models have made significant progress in generating vivid visual details, they can…
We present a novel deep learning based algorithm for video inpainting. Video inpainting is a process of completing corrupted or missing regions in videos. Video inpainting has additional challenges compared to image inpainting due to the…
We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent 'Deep Image Prior' (DIP) that exploits convolutional network architectures to…
In this work, we introduce a challenging image restoration task, referred to as SuperInpaint, which aims to reconstruct missing regions in low-resolution images and generate completed images with arbitrarily higher resolutions. We have…
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with…
We present a deep learning approach for learning the joint semantic embeddings of images and captions in a Euclidean space, such that the semantic similarity is approximated by the L2 distances in the embedding space. For that, we introduce…
Generic image inpainting aims to complete a corrupted image by borrowing surrounding information, which barely generates novel content. By contrast, multi-modal inpainting provides more flexible and useful controls on the inpainted content,…
Recently, learning frameworks have shown the capability of inferring the accurate shape, pose, and texture of an object from a single RGB image. However, current methods are trained on image collections of a single category in order to…
We propose a novel probabilistic dimensionality reduction framework that can naturally integrate the generative model and the locality information of data. Based on this framework, we present a new model, which is able to learn a smooth…
Recent advances in deep generative adversarial networks (GAN) and self-attention mechanism have led to significant improvements in the challenging task of inpainting large missing regions in an image. These methods integrate self-attention…
Language grounding aims at linking the symbolic representation of language (e.g., words) into the rich perceptual knowledge of the outside world. The general approach is to embed both textual and visual information into a common space -the…
Image Inpainting is one of the very popular tasks in the field of image processing with broad applications in computer vision. In various practical applications, images are often deteriorated by noise due to the presence of corrupted, lost,…
Recent works on representation learning for Knowledge Graphs have moved beyond the problem of link prediction, to answering queries of an arbitrary structure. Existing methods are based on ad-hoc mechanisms that require training with a…