Related papers: TransMatting: Tri-token Equipped Transformer Model…

Natural image matting estimates the alpha values of unknown regions in the trimap. Recently, deep learning based methods propagate the alpha values from the known regions to unknown regions according to the similarity between them. However,…

This paper presents a Transformer-based image compression system that allows for a variable image quality objective according to the user's preference. Optimizing a learned codec for different quality objectives leads to reconstructed…

Enabling image generation models to be spatially controlled is an important area of research, empowering users to better generate images according to their own fine-grained specifications via e.g. edge maps, poses. Although this task has…

This paper proposes a novel deep learning-based video object matting method that can achieve temporally coherent matting results. Its key component is an attention-based temporal aggregation module that maximizes image matting networks'…

Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…

Recent image-to-image translation works have been transferred from supervised to unsupervised settings due to the expensive cost of capturing or labeling large amounts of paired data. However, current unsupervised methods using the…

This work proposes a new image analysis tool called Label Consistent Transform Learning (LCTL). Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency…

Multi-illuminant color constancy methods aim to eliminate local color casts within an image through pixel-wise illuminant estimation. Existing methods mainly employ deep learning to establish a direct mapping between an image and its…

Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks. While reinforcement learning (RL) based agents can generate a stroke sequence step…

Tone style transfer for photo retouching aims to adapt the stylistic tone of the reference image to a given content image. However, the lack of high-quality large-scale triplet datasets with stylized ground truth forces existing methods to…

Tone-mapping plays an essential role in high dynamic range (HDR) imaging. It aims to preserve visual information of HDR images in a medium with a limited dynamic range. Although many works have been proposed to provide tone-mapped results…

This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark…

Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to…

Scanpath prediction in 360{\deg} images can help realize rapid rendering and better user interaction in Virtual/Augmented Reality applications. However, existing scanpath prediction models for 360{\deg} images execute scanpath prediction on…

Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively…

We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is based on background matting, where an additional frame of the background…

We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting. To perform this mapping, we use convolutional neural networks trained…

Human matting, high quality extraction of humans from natural images, is crucial for a wide variety of applications. Since the matting problem is severely under-constrained, most previous methods require user interactions to take user…

In this paper, we propose a principled Perceptual Adversarial Networks (PAN) for image-to-image transformation tasks. Unlike existing application-specific algorithms, PAN provides a generic framework of learning mapping relationship between…

Cross-modality magnetic resonance (MR) image synthesis can be used to generate missing modalities from given ones. Existing (supervised learning) methods often require a large number of paired multi-modal data to train an effective…