CYCheng Yang

Cheng Yang

*This is an algorithmically generated author record based on publicly available information.

Cheng Yang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    QS-NeRV: Real-Time Quality-Scalable Decoding with Neural Representation for Videos

    by Chang Wu, Guancheng Quan, Gang He, Xin-Quan Lai, Yunsong Li, Wenxin Yu, Xianmeng Lin, Cheng Yang

    In this paper, we propose a neural representation for videos that enables real-time quality-scalable decoding, called QS-NeRV. QS-NeRV comprises a Self-Learning Distribution Mapping Network (SDMN) and Extensible Enhancement Networks (EENs). Firstly, SDMN functions as the base layer (BL) for scalable video coding, focusing on encoding videos of lower quality. Within SDMN, we employ a methodology that minimizes the bitstream overhead to achieve efficient information exchange between the encoder and decoder instead of direct transmission. Specifically, we utilize an invertible network to map the multi-scale information obtained from the encoder to a specific distribution. Subsequently, during the decoding process, this information is recovered from a randomly sampled latent variable to assist the decoder in achieving improved reconstruction performance. Secondly, EENs serve as the enhancement layers (ELs) and are trained in an overfitting manner to obtain robust restoration capability. By integrating the fixed BL bitstream with the parameters of EEN as an extension pack, the decoder can produce higher-quality enhanced videos. Furthermore, the scalability of the method allows for adjusting the number of combined packs to accommodate diverse quality requirements. Experimental results demonstrate our proposed QS-NeRV outperforms the state-of-the-art real-time decoding INR-based methods on various datasets for video compression and interpolation tasks.


  • Open Access

    An End-to-End Real-World Camera Imaging Pipeline

    by Kepeng Xu, Zijia Ma, Li Xu, Gang He, Yunsong Li, Wenxin Yu, Taichu Han, Cheng Yang

    Recent advances in neural camera imaging pipelines have demonstrated notable progress. Nevertheless, the real-world imaging pipeline still faces challenges including the lack of joint optimization in system components, computational redundancies, and optical distortions such as lens shading. In light of this, we propose an end-to-end camera imaging pipeline (RealCamNet) to enhance real-world camera imaging performance. Our methodology diverges from conventional, fragmented multi-stage image signal processing towards end-to-end architecture. This architecture facilitates joint optimization across the full pipeline and the restoration of coordinate-biased distortions. RealCamNet is designed for high-quality conversion from RAW to RGB and compact image compression. Specifically, we deeply analyze coordinate-dependent optical distortions, e.g., vignetting and dark shading, and design a novel Coordinate-Aware Distortion Restoration (CADR) module to restore coordinate-biased distortions. Furthermore, we propose a Coordinate-Independent Mapping Compression (CIMC) module to implement tone mapping and redundant information compression. Existing datasets suffer from misalignment and overly idealized conditions, making them inadequate for training real-world imaging pipelines. Therefore, we collected a real-world imaging dataset. Experiment results show that RealCamNet achieves the best rate-distortion performance with lower inference latency.


  • Unequal error protection for S3AC coding based on expanding window fountain codes

    by Liuyue Su, Ge Gao, Cheng Yang, Ruimin Hu, Xiaochen Wang, Xin Su

    This paper presents a coding scheme to improve the performance of three-dimensional (3D) audio. The scheme is designed by the idea of joint source channel coding (JSCC) and is implemented by Expanding Window Fountain (EWF) codes for the 3D audio bitstreams after source coding of spatial squeeze surround audio coding (S3AC). EWF is one of unequal error protection (UEP) LT codes and the proposed scheme is achieved by that method for the case of two levels. Different from other transmissions with equal error protection (EEP) for each part of bitstreams, when transmitting the two parts of the bitstreams with downmixed mono signals and spatial side information after S3AC coding, this approach provides more protection to the part of spatial side information and comparatively less protection to the downmixed mono signals, and results in the improvement of the performance of the reproduced 3D audio especially on the aspect of the spatial perception. Objective simulation experiment has shown the proposed UEP scheme achieves a better performance than the EEP scheme on the aspect of spatial perception, for the bits error rates (BER) of spatial parameters can decrease dramatically to a low value of about 10-4, but BERs of downmixed mono signals and the case of EEP just decrease slightly to about 10-3.