In this paper, we introduce a new approach for high-quality multi-exposu...
Recent deep learning-based optical flow estimators have exhibited impres...
This paper presents a novel network structure with illumination-aware ga...
In this paper, we propose an iterative framework, which consists of two
...
Correlation based stereo matching has achieved outstanding performance, ...
Image Quality Assessment (IQA) is a challenging task that requires train...
Accurate segmentation of lesions is crucial for diagnosis and treatment ...
Diffusion models have achieved promising results in image restoration ta...
This paper proposes a hybrid synthesis method for multi-exposure image f...
We study the problem of estimating optical flow from event cameras. One
...
Traditional image stitching approaches tend to leverage increasingly com...
Existing homography and optical flow methods are erroneous in challengin...
Neural Architecture Search (NAS) is an automatic technique that can sear...
This paper proposes a deep recurrent Rotation Averaging Graph Optimizer
...
Homography estimation is erroneous in the case of large-baseline due to ...
We present a novel camera path optimization framework for the task of on...
High dynamic range (HDR) deghosting algorithms aim to generate ghost-fre...
Obtaining the ground truth labels from a video is challenging since the
...
Not everybody can be equipped with professional photography skills and
s...
This paper reviews the challenge on constrained high dynamic range (HDR)...
To achieve promising results on removing noise from real-world images, m...
Estimating homography from an image pair is a fundamental problem in ima...
This work addresses the Burst Super-Resolution (BurstSR) task using a ne...
With the advent of convolutional neural networks, stereo matching algori...
Stitched images provide a wide field-of-view (FoV) but suffer from unple...
In this paper, we tackle the problem of blind image super-resolution(SR)...
Estimating per-pixel motion between video frames, known as optical flow,...
We propose a semi-supervised network for wide-angle portraits correction...
Homography estimation is an important task in computer vision, such as i...
Traditional feature-based image stitching technologies rely heavily on
f...
This paper reviews the NTIRE2021 challenge on burst super-resolution. Gi...
Data association is important in the point cloud registration. In this w...
In this paper, we present an attention-guided deformable convolutional
n...
Image denoising is one of the most critical problems in mobile photo
pro...
Wide-angle portraits often enjoy expanded views. However, they contain
p...
We present an unsupervised optical flow estimation method by proposing a...
In this paper, we introduce a new framework for unsupervised deep homogr...
In this paper, we present D2C-SR, a novel framework for the task of imag...
Existing optical flow methods are erroneous in challenging scenes, such ...
We present a new pipeline for holistic 3D scene understanding from a sin...
Point cloud registration is a key task in many computational fields. Pre...
The paper proposes a method to effectively fuse multi-exposure inputs an...
Mobile captured images can be aligned using their gyroscope sensors. Opt...
The paper proposes a solution based on Generative Adversarial Network (G...
In this paper, we introduce NBNet, a novel framework for image denoising...
We present an unsupervised learning approach for optical flow estimation...
A single perturbation can pose the most natural images to be misclassifi...
Occlusion is an inevitable and critical problem in unsupervised optical ...
3D object detection has become an emerging task in autonomous driving
sc...
Accurate 3D object detection from point clouds has become a crucial comp...