1 code implementation • 15 Mar 2024 • Feng Li, Yixuan Wu, Zichao Liang, Runmin Cong, Huihui Bai, Yao Zhao, Meng Wang
BlindDiff seamlessly integrates the MAP-based optimization into DMs, which constructs a joint distribution of the low-resolution (LR) observation, high-resolution (HR) data, and degradation kernels for the data and kernel priors, and solves the blind SR problem by unfolding MAP approach along with the reverse process.
no code implementations • 11 Mar 2024 • Xiaoyang Wang, Huihui Bai, Limin Yu, Yao Zhao, Jimin Xiao
Inspired by the low-density separation assumption in semi-supervised learning, our key insight is that feature density can shed a light on the most promising direction for the segmentation classifier to explore, which is the regions with lower density.
1 code implementation • 1 Mar 2024 • Yuxi Liu, Wenhan Yang, Huihui Bai, Yunchao Wei, Yao Zhao
However, there is no prior research on neural transform that focuses on specific regions.
Ranked #1 on Image Compression on kodak
1 code implementation • 27 Jun 2023 • Anqi Li, Feng Li, Jiaxin Han, Huihui Bai, Runmin Cong, Chunjie Zhang, Meng Wang, Weisi Lin, Yao Zhao
Extensive experiments have demonstrated that our approach outperforms recent state-of-the-art methods in R-D performance, visual quality, and downstream applications, at very low bitrates.
1 code implementation • 15 Jun 2023 • Dongyi Zhang, Feng Li, Man Liu, Runmin Cong, Huihui Bai, Meng Wang, Yao Zhao
In this work, we explore the potential of resolution fields in scalable image compression and propose the reciprocal pyramid network (RPN) that fulfills the need for more adaptable and versatile compression.
1 code implementation • CVPR 2023 • Man Liu, Feng Li, Chunjie Zhang, Yunchao Wei, Huihui Bai, Yao Zhao
Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain, relying on the intrinsic interactions between visual and semantic information.
1 code implementation • 3 Dec 2022 • Yixuan Wu, Feng Li, Huihui Bai, Weisi Lin, Runmin Cong, Yao Zhao
In this paper, we analyze the degradation of a high-resolution (HR) image from image intrinsic components according to a degradation-based formulation model.
1 code implementation • 3 Dec 2022 • Feng Li, Yixuan Wu, Huihui Bai, Weisi Lin, Runmin Cong, Yao Zhao
Recent blind SR methods suggest to reconstruct SR images relying on blur kernel estimation.
1 code implementation • CVPR 2021 • Lingzhi He, Hongguang Zhu, Feng Li, Huihui Bai, Runmin Cong, Chunjie Zhang, Chunyu Lin, Meiqin Liu, Yao Zhao
Depth maps obtained by commercial depth sensors are always in low-resolution, making it difficult to be used in various computer vision tasks.
1 code implementation • 29 Oct 2020 • Feng Li, Runmin Cong, Huihui Bai, Yifan He, Yao Zhao, Ce Zhu
In this paper, we present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction.
1 code implementation • 24 Apr 2020 • Feng Li, Runming Cong, Huihui Bai, Yifan He
Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature.
1 code implementation • 12 Jan 2020 • Lijun Zhao, Jinjing Zhang, Fan Zhang, Anhong Wang, Huihui Bai, Yao Zhao
Most deep image smoothing operators are always trained repetitively when different explicit structure-texture pairs are employed as label images for each algorithm configured with different parameters.
2 code implementations • 12 Jan 2020 • Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao
In this paper, we introduce a deep multiple description coding (MDC) framework optimized by minimizing multiple description (MD) compressive loss.
1 code implementation • 5 Nov 2018 • Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao
Secondly, two entropy estimation networks are learned to estimate the informative amounts of the quantized tensors, which can further supervise the learning of multiple description encoder network to represent the input image delicately.
1 code implementation • 22 Jun 2018 • Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao
In order to train RSN network and IDN network together in an end-to-end fashion, our VCN network intimates projection from the re-sampled vectors to the IDN-decoded image.
no code implementations • 2 Feb 2018 • Lijun Zhao, Huihui Bai, Feng Li, Anhong Wang, Yao Zhao
Firstly, given one input image, feature description neural network (FDNN) is used to generate a new representation of this image, so that this image representation can be more efficiently compressed by standard codec, as compared to the input image.
no code implementations • 20 Jan 2018 • Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao
Thirdly, multiple description virtual codec network (MDVCN) is proposed to bridge the gap between MDGN network and MDRN network in order to train an end-to-end MDC framework.
1 code implementation • 16 Dec 2017 • Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao
Due to the challenge of directly learning a non-linear function for a standard codec based on convolutional neural network, we propose to learn a virtual codec neural network to approximate the projection from the valid description image to the post-processed compressed image, so that the gradient could be efficiently back-propagated from the post-processing neural network to the feature description neural network during training.
no code implementations • 30 Aug 2017 • Lijun Zhao, Huihui Bai, Jie Liang, Bing Zeng, Anhong Wang, Yao Zhao
Firstly, given the low-resolution depth image and low-resolution color image, a generative network is proposed to leverage mutual information of color image and depth image to enhance each other in consideration of the geometry structural dependency of color-depth image in the same scene.
no code implementations • 9 Jul 2017 • Lijun Zhao, Jie Liang, Huihui Bai, Lili Meng, Anhong Wang, Yao Zhao
Both frameworks employ the division of gradient and the local activity measurement to achieve noise removal.