Search
Results
-
CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution
(2023)2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Learning continuous image representations is recently gaining popularity for image super-resolution (SR) because of its ability to reconstruct high-resolution images with arbitrary scales from low-resolution inputs. Existing methods mostly ensemble nearby features to predict the new pixel at any queried coordinate in the SR image. Such a local ensemble suffers from some limitations: i) it has no learnable parameters and it neglects the ...Conference Paper -
HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)The rapid development of deep learning provides a better solution for the end-to-end reconstruction of hyperspectral image (HSI). However, existing learning-based methods have two major defects. Firstly, networks with self-attention usually sacrifice internal resolution to balance model performance against complexity, losing fine-grained high-resolution (HR) features. Secondly, even if the optimization focusing on spatial-spectral domain ...Conference Paper -
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement in the coded aperture snapshot spectral imaging (CASSI) system. The HSI representations are highly similar and correlated across the spectral dimension. Modeling the inter-spectra interactions is beneficial for HSI reconstruction. However, existing CNN-based methods show limitations in capturing spectral-wise similarity and ...Conference Paper -
Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction
(2022)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2022Many learning-based algorithms have been developed to solve the inverse problem of coded aperture snapshot spectral imaging (CASSI). However, CNN-based methods show limitations in capturing long-range dependencies. Previous Transformer-based methods densely sample tokens, some of which are uninformative, and calculate multi-head self-attention (MSA) between some tokens that are unrelated in content. In this paper, we propose a novel ...Conference Paper -
NTIRE 2022 Spectral Recovery Challenge and Data Set
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)This paper reviews the third biennial challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. This challenge presents the "ARAD 1K" data set: a new, larger-than-ever natural hyperspectral image data set containing 1,000 images. Challenge participants were required to recover hyperspectral information from synthetically generated JPEG-compressed RGB ...Conference Paper -
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image to its hyperspectral image (HSI). These CNN-based methods achieve impressive restoration performance while showing limitations in capturing the lon-grange dependencies and self-similarity prior. To cope with this problem, we propose a novel Transformer-based ...Conference Paper -
Flow-Guided Sparse Transformer for Video Deblurring
(2022)Proceedings of Machine Learning Research ~ Proceedings of the 39th International Conference on Machine LearningExploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range dependencies and modeling non-local self-similarity. In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring. In FGST, we customize a self-attention module, Flow-Guided Sparse Window-based Multi-head Self-Attention ...Conference Paper -
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion
(2023)2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Multi-modality (MM) image fusion aims to render fused images that maintain the merits of different modalities, e.g., functional highlight and detailed textures. To tackle the challenge in modeling cross-modality features and decomposing desirable modality-specific and modality-shared features, we propose a novel Correlation-Driven feature Decomposition Fusion (CDDFuse) network. Firstly, CDDFuse uses Restormer blocks to extract cross-modality ...Conference Paper -
Knowledge Distillation based Degradation Estimation for Blind Super-Resolution
(2023)The Eleventh International Conference on Learning RepresentationsConference Paper -
Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution
(2024)2023 IEEE/CVF International Conference on Computer Vision (ICCV)Guided depth map super-resolution (GDSR), as a hot topic in multi-modal image processing, aims to upsample low-resolution (LR) depth maps with additional information involved in high-resolution (HR) RGB images from the same scene. The critical step of this task is to effectively extract domain-shared and domain-private RGB/depth features. In addition, three detailed issues, namely blurry edges, noisy surfaces, and over-transferred RGB ...Conference Paper