Ning Zhang

Ning Zhang

Auto-generated profile, based on publicly available information

Ning Zhang

Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 June 2021 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
NZNing Zhang
Ning Zhang
YZYang Zhao
Yang Zhao
CWChao Wang
Chao Wang
RWRonggang Wang
Ronggang Wang
Tone mapping operators (TMOs) can compress the range of high dynamic range (HDR) images so that they can be displayed normally on the low dynamic range (LDR) devices. Recent TMOs based on deep neural networks can produce impressive results, but there are still some shortcomings. On the one hand, their supervised learning procedure requires a high-quality paired dataset which is hard to be accessed. On the other hand, they are too slow and heavy to meet the needs of practical applications. This paper proposes a real-time deep semi-supervised learning TMO to solve the above problems. The proposed method learns in a semi-supervised manner by combining the adversarial loss, cycle consistency loss, and the pixel-wise loss. The first two can simulate the image distributions in the real world from the unpaired LDR data and the latter can learn the guidance of paired LDR labels. In this way, the proposed method only requires HDR sources, unpaired high-quality LDR images, and a few well tone-mapped HDR-LDR pairs as training data. Furthermore, the proposed method divides tone mapping into luminance mapping and saturation adjustment and then processes them simultaneously. By this strategy, we can reconstruct each component more precisely. Based on the aforementioned improvements, we propose a lightweight tone mapping network that is efficient in tone mapping task (up to 5000x parameters-saving and 27x time-saving compared to the learning-based TMOs). Both quantitative and qualitative results demonstrate that the proposed method performs favorable against state-of-the-art TMOs.

26 October 2023
Verified
Conference Paper
Open access
SGSha Guo
Sha Guo
ZCZhuo Chen
Zhuo Chen
YZYang Zhao
Yang Zhao
NZNing Zhang
Ning Zhang
XLXiaotong Li
Xiaotong Li
LDLingyu Duan
Lingyu Duan
Traditional image codecs prioritize signal fidelity and human perception, often neglecting machine vision tasks. Deep learning approaches have shown promising coding performance by leveraging rich semantic embeddings that can be optimized for both human and machine vision. However, these compact embeddings struggle to represent low-level details like contours and textures, leading to imperfect reconstructions. Additionally, existing learning-based coding tools lack scalability. To address these challenges, this paper presents a content-adaptive diffusion model for scalable image compression. The method encodes accurate texture through a diffusion process, enhancing human perception while preserving important features for machine vision tasks. It employs a Markov palette diffusion model with commonly-used feature extractors and image generators, enabling efficient data compression. By utilizing collaborative texture-semantic feature extraction and pseudo-label generation, the approach accurately learns texture information. A content-adaptive Markov palette diffusion model is then applied to capture both low-level texture and high-level semantic knowledge in a scalable manner. This framework enables elegant compression ratio control by flexibly selecting intermediate diffusion states, eliminating the need for deep learning model re-training at different operating points. Extensive experiments demonstrate the effectiveness of the proposed framework in image reconstruction and downstream machine vision tasks such as object detection, segmentation, and facial landmark detection. It achieves superior perceptual quality scores compared to state-of-the-art methods.

2 February 2023 in CAAI Transactions on Intelligence Technology
Verified
Journal Article
Open access
NZNing Zhang
Ning Zhang
YYYuyao Ye
Yuyao Ye
YZYang Zhao
Yang Zhao
XLXufeng Li
Xufeng Li
RWRonggang Wang
Ronggang Wang
Inverse tone mapping technique is widely used to restore the lost textures from a single low dynamic range image. Recently, many stack‐based deep inverse tone mapping networks have achieved impressive results by estimating a set of multi‐exposure images from a single low dynamic range input. However, there are still some limitations. On the one hand, these methods usually set a fixed length for the estimated multi‐exposure stack, which may introduce computational redundancy or cause inaccurate results. On the other hand, they neglect that the difficulties of estimating each exposure value are different and use the identical model to increase or decrease exposure value. To solve these problems, the authors design an exposure decision network to adaptively determine the number of times the exposure of low dynamic range input should be increased or decreased. Meanwhile, the authors decouple the increasing/decreasing process into two sub‐modules, exposure adjustment and optional detail recovery, based on the characteristics of different variations of exposure values. With these improvements, this method can fast and flexibly estimate the multi‐exposure stack from a single low dynamic range image. Experiments on several datasets demonstrate the advantages of the proposed method compared to state‐of‐the‐art inverse tone mapping methods.

8 October 2024 in arXiv
Verified
Preprint
Open access
PDF file
SGSha Guo
Sha Guo
ZCZhuo Chen
Zhuo Chen
YZYang Zhao
Yang Zhao
NZNing Zhang
Ning Zhang
XLXiaotong Li
Xiaotong Li
LDLingyu Duan
Lingyu Duan
Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding performance by utilizing rich semantic embeddings optimized for both human and machine vision. However, these compact embeddings struggle to capture fine details such as contours and textures, resulting in imperfect reconstructions. Furthermore, existing learning-based codecs lack scalability. To address these limitations, this paper introduces a content-adaptive diffusion model for scalable image compression. The proposed method encodes fine textures through a diffusion process, enhancing perceptual quality while preserving essential features for machine vision tasks. The approach employs a Markov palette diffusion model combined with widely used feature extractors and image generators, enabling efficient data compression. By leveraging collaborative texture-semantic feature extraction and pseudo-label generation, the method accurately captures texture information. A content-adaptive Markov palette diffusion model is then applied to represent both low-level textures and high-level semantic content in a scalable manner. This framework offers flexible control over compression ratios by selecting intermediate diffusion states, eliminating the need for retraining deep learning models at different operating points. Extensive experiments demonstrate the effectiveness of the proposed framework in both image reconstruction and downstream machine vision tasks such as object detection, segmentation, and facial landmark detection, achieving superior perceptual quality compared to state-of-the-art methods.