Related papers: Deep Video Inpainting Guided by Audio-Visual Self-…
Video restoration and enhancement are critical not only for improving visual quality, but also as essential pre-processing steps to boost the performance of a wide range of downstream computer vision tasks. This survey presents a…
Audio inpainting refers to signal processing techniques that aim at restoring missing or corrupted consecutive samples in audio signals. Prior works have shown that $\ell_1$- minimization with appropriate weighting is capable of solving…
With its significant performance improvements, the deep learning paradigm has become a standard tool for modern image denoisers. While promising performance has been shown on seen noise distributions, existing approaches often suffer from…
Transient loud intrusions, often occurring in noisy environments, can completely overpower speech signal and lead to an inevitable loss of information. While existing algorithms for noise suppression can yield impressive results, their…
Given an input painting, we reconstruct a time-lapse video of how it may have been painted. We formulate this as an autoregressive image generation problem, in which an initially blank "canvas" is iteratively updated. The model learns from…
3D scene reconstruction from multiple views is an important classical problem in computer vision. Deep learning based approaches have recently demonstrated impressive reconstruction results. When training such models, self-supervised…
We propose the first deep learning solution to video frame inpainting, a challenging instance of the general video inpainting problem with applications in video editing, manipulation, and forensics. Our task is less ambiguous than frame…
Existing deep learning-based image inpainting methods typically rely on convolutional networks with RGB images to reconstruct images. However, relying exclusively on RGB images may neglect important depth information, which plays a critical…
Convolutional neural networks contain strong priors for generating natural looking images [1]. These priors enable image denoising, super resolution, and inpainting in an unsupervised manner. Previous attempts to demonstrate similar ideas…
Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' in CNNs. To this end,…
The perception of transparent objects is one of the well-known challenges in computer vision. Conventional depth sensors have difficulty in sensing the depth of transparent objects due to refraction and reflection of light. Previous…
Supervised learning with a convolutional neural network is recognized as a powerful means of image restoration. However, most such methods have been designed for application to grayscale and/or color images; therefore, they have limited…
Diffusion probabilistic models learn to remove noise added during training, generating novel data (e.g., images) from Gaussian noise through sequential denoising. However, conditioning the generative process on corrupted or masked images is…
Autonomous driving is a multi-task problem requiring a deep understanding of the visual environment. End-to-end autonomous systems have attracted increasing interest as a method of learning to drive without exhaustively programming…
This paper studies audio-visual noise suppression for egocentric videos -- where the speaker is not captured in the video. Instead, potential noise sources are visible on screen with the camera emulating the off-screen speaker's view of the…
The objective of this paper is self-supervised learning of feature embeddings that are suitable for matching correspondences along the videos, which we term correspondence flow. By leveraging the natural spatial-temporal coherence in…
The need for a large amount of labeled data in the supervised setting has led recent studies to utilize self-supervised learning to pre-train deep neural networks using unlabeled data. Many self-supervised training strategies have been…
Reconstructing 4D dynamic scenes from casually captured monocular videos is valuable but highly challenging, as each timestamp is observed from a single viewpoint. We introduce Vivid4D, a novel approach that enhances 4D monocular video…
Patch-based methods and deep networks have been employed to tackle image inpainting problem, with their own strengths and weaknesses. Patch-based methods are capable of restoring a missing region with high-quality texture through searching…
Training deep neural networks typically requires large amounts of labeled data which may be scarce or expensive to obtain for a particular target domain. As an alternative, we can leverage webly-supervised data (i.e. results from a public…