Abstract Machine learning has become the state-of-the-art technique for many tasks
including computer vision, natural language processing, speech processing tasks, etc …

Nowadays, computer vision with 3D (dimension) object detection and 6D (degree of
freedom) pose assumptions are widely discussed and studied in the field. In the 3D object …

We propose Image-to-Image Schr\" odinger Bridge (I $^ 2$ SB), a new class of conditional
diffusion models that directly learn the nonlinear diffusion processes between two given …

This paper presents a stochastic differential equation (SDE) approach for general-purpose
image restoration. The key construction consists in a mean-reverting SDE that transforms a …

The tradeoff between receptive field size and efficiency is a crucial issue in low level vision.
Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of …

This paper introduces a novel large dataset for example-based single image super-
resolution and studies the state-of-the-art as emerged from the NTIRE 2017 challenge. The …

Image restoration aims to reconstruct a high-quality image from its corrupted version, playing
essential roles in many scenarios. Recent years have witnessed a paradigm shift in image …

Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image
and the blur kernel given a blurry image. Recent progress on image deblurring always …

In computer vision, convolutional networks (CNNs) often adopt pooling to enlarge receptive
field which has the advantage of low computational complexity. However, pooling can cause …

Image denoising—removal of additive white Gaussian noise from an image—is one of the
oldest and most studied problems in image processing. Extensive work over several …