Zhijie Huang

Zhijie Huang

Auto-generated profile, based on publicly available information

Zhijie Huang

Wangxuan Institute of Computer Technology, Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
15 June 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZHZhijie Huang
Zhijie Huang
JSJun Sun
Jun Sun
XGXiaopeng Guo
Xiaopeng Guo
MSMingyu Shang
Mingyu Shang
Recently, many researches on convolution neural network (CNN) based in-loop filters have been proposed to improve coding efficiency. However, most existing CNN based filters tend to train and deploy multiple networks for various quantization parameters (QP) and frame types (FT), which drastically increases resources in training these models and the memory burdens for video codec. In this paper, we propose a novel variable CNN (VCNN) based in-loop filter for VVC, which can effectively handle the compressed videos with different QPs and FTs via a single model. Specifically, an efficient and flexible attention module is developed to recalibrate features according to QPs or FTs. Then we embed the module into the residual block so that these informative features can be continuously utilized in the residual learning process. To minimize the information loss in the learning process of the entire network, we utilize a residual feature aggregation module (RFA) for more efficient feature extraction. Based on it, an efficient network architecture VCNN is designed that can not only effectively reduce compression artifacts, but also can be adaptive to various QPs and FTs. To address training data imbalance on various QPs and FTs and improve the robustness of the model, a focal mean square error loss function is employed to train the proposed network. Then we integrate the VCNN into VVC as an additional tool of in-loop filters after the deblocking filter. Extensive experimental results show that our VCNN approach obtains on average 3.63%, 4.36%, 4.23%, 3.56% under all intra, low-delay P, low-delay, and random access configurations, respectively, which is even better than QP-Separate models.

3 June 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZHZhijie Huang
Zhijie Huang
JSJun Sun
Jun Sun
XGXiaopeng Guo
Xiaopeng Guo
MSMingyu Shang
Mingyu Shang
Deep learning-based in-loop filters have recently demonstrated great improvement for both coding efficiency and subjective quality in video coding. However, most existing deep learning-based in-loop filters tend to develop a sophisticated model in exchange for good performance, and they employ a single network structure to all reconstructed samples, which lack sufficient adaptiveness to the various video content, limiting their performances to some extent. In contrast, this paper proposes an adaptive deep reinforcement learning-based in-loop filter (ARLF) for versatile video coding (VVC). Specifically, we treat the filtering as a decision-making process and employ an agent to select an appropriate network by leveraging recent advances in deep reinforcement learning. To this end, we develop a lightweight backbone and utilize it to design a network set $\mathcal {S}$ containing networks with different complexities. Then a simple but efficient agent network is designed to predict the optimal network from $\mathcal {S}$ , which makes the model adaptive to various video contents. To improve the robustness of our model, a two-stage training scheme is further proposed to train the agent and tune the network set. The coding tree unit (CTU) is seen as the basic unit for the in-loop filtering processing. A CTU level control flag is applied in the sense of rate-distortion optimization (RDO). Extensive experimental results show that our ARLF approach obtains on average 2.17%, 2.65%, 2.58%, 2.51% under all-intra, low-delay P, low-delay, and random access configurations, respectively. Compared with other deep learning-based methods, the proposed approach can achieve better performance with low computation complexity.

25 February 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
ZHZhijie Huang
Zhijie Huang
JSJun Sun
Jun Sun
XGXiaopeng Guo
Xiaopeng Guo
Deep neural networks have achieved remarkable success in HEVC compressed video quality enhancement. However, most existing multiframe-based methods either deliver unsatisfactory results or consume a significant amount of resources to leverage temporal information of neighboring frames. For the sake of practicality, a thorough investigation of the architecture design of the video quality enhancement network regarding enhancement performance, model parameters, and running speed is essential. In this article, we first propose an efficient alignment module that can quickly and accurately aggregate the spatiotemporal information of neighboring frames. The proposed module estimates deformable offsets progressively in lower-resolution space motivated by the observation of offset correlations between adjacent pixels. Then, the quantization parameter (QP) that represents compression level prior knowledge is utilized to guide aligned feature enhancement. By combining alignment feature distillation with residual feature correction, we obtain an efficient QP attention block. To save the storage space of the network, we design a hash buffer to store QP embedding features. These efficient components allow our network to effectively exploit temporal redundancies and obtain favorable enhancement capability while maintaining a lightweight structure and fast running speed. Extensive experiments demonstrate that the proposed approach outperforms state-of-the-art methods over different QPs by up to 0.09 to 0.11 dB, whereas the inference time can be reduced by up to 69%.

15 July 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
TSTianyi Sun
Tianyi Sun
YWYanze Wang
Yanze Wang
ZHZhijie Huang
Zhijie Huang
JSJun Sun
Jun Sun
The Versatile Video Coding (VVC) standard introduces a quad-tree with a nested multi-type tree (QTMT) partition structure to improve the rate-distortion (RD) performance, but this leads to a substantial increase in encoding complexity. Previous studies have labeled partition modes of CUs using hard targets (i.e., one-hot labels) generated by VVC reference software (VTM), which is challenging for neural networks to predict accurately. Furthermore, in earlier works, the VVC restrictions are not incorporated into convolutional neural network (CNN), not fully exploiting the predicting capacity of CNN. In this paper, we propose a novel soft-target and restriction-aware neural network (STRANet) to address these issues. Firstly, inspired by the observation that a CU may split differently under various circumstances, we collect these RD costs and precisely estimate the probability of each partition mode to generate a soft target. Secondly, our neural network incorporates QP and restriction type through attention modules so as to output predictions that are standard-compliant with simple post-processing. Thirdly, Window Attention Module, a combination of CNN and attention mechanism, is adopted to further enhance performance on GPU. Through the application of these methods, STRANet reduces encoding time by 51.84% and 61.00% with 0.44% and 0.84% Bjøntegaard delta bit-rate (BD-BR) increase, superior to state-of-the-art methods. The code has been released at https://github.com/cppppp/STRANet.

26 July 2024
Verified
Book Chapter
Closed access
PDF file
XGXiaopeng Guo
Xiaopeng Guo
MSMaojing Shu
Maojing Shu
ZHZhijie Huang
Zhijie Huang
JLJun Liu
Jun Liu
JSJun Sun
Jun Sun

1 September 2019
Verified
Conference Paper
Closed access
YLYunchang Li
Yunchang Li
ZHZhijie Huang
Zhijie Huang
JSJun Sun
Jun Sun
Inserting a logo into HEVC video streams is highly demanded in video applications. In this paper, we present an efficient logo insertion method for video coding in HEVC. To reduce the impact of inserted logo, the proposed method mitigates the encoding dependence on logo by partitioning the video frame into separated regions. For lossless coding region, we reduce the bit rate overhead of lossless coding according to an error propagation model. For information reusing region, we partly re-encode the quality-loss area to maintain the encoding quality. The computational complexity is reduced by reusing information. Experimental results show that the proposed method achieves a significant speedup ratio of 52 times on average with only 1.43% bit rate increase compared with direct encoding using unmodified HM software.