publications

2026

1. 

   TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data

   Zhengxue Cheng^♯, Yan Zhao, Keyu Wang, Hengdi Zhang, and Li Song

   In International Conference on Learning Representations (ICLR), 2026

2025

1. 

   Instance-Adaptive Spatial-Temporal Enhancement for Efficient Video Compression

   Yan Zhao, Zhengxue Cheng^♯, Jiangchuan Li, Donghui Feng, Qunshan Gu, Qi Wang, Guo Lu, and Li Song^♯

   IEEE Trans. on Image Processing, 2025

   DOI

2. 

   Linear Attention Modeling for Learned Image Compression

   Donghui Feng^*, Zhengxue Cheng^*, Shen Wang, Ronghua Wu, Hongwei Hu, Guo Lu, and Li Song^♯

   In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Jun 2025
3. SemanticGarment: Semantic-Controlled Generation and Editing of 3D Gaussian Garments

   Ruiyan Wang, Zhengxue Cheng^♯, Zonghao Lin, Jun Ling, Yuzhou Liu, Yanru An, Rong Xie, and Li Song^♯

   In Proceedings of the 33rd ACM International Conference on Multimedia, Dublin, Ireland, Jun 2025

   DOI
4. MultiEgo: A Multi-View Egocentric Video Dataset for 4D Scene Reconstruction

   Bate Li, Houqiang Zhong, Zhengue Cheng^♯, Qiang Hu, Qiang Wang, Li Song^♯, and Wenjun Zhang^♯

   In Proceedings of the 33rd ACM International Conference on Multimedia, Dublin, Ireland, Jun 2025

   DOI
5. PA-HOI: A Physics-Aware Human and Object Interaction Dataset

   Ruiyan Wang, Lin Zuo, Zonghao Lin, Qiang Wang, Zhengxue Cheng^♯, Rong Xie, Jun Ling^♯, and Li Song^♯

   In Proceedings of the 33rd ACM International Conference on Multimedia, Dublin, Ireland, Jun 2025

   DOI

6. 

   L3TC: leveraging RWKV for learned lossless low-complexity text compression

   Junxuan Zhang^*, Zhengxue Cheng^*♯, Yan Zhao, Shihao Wang, Dajiang Zhou, Guo Lu, and Li Song

   In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, Jun 2025

   DOI

7. 

   OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution

   Xinning Chai, Zhengxue Cheng^♯, Yuhong Zhang, Hengsheng Zhang, Yingsheng Qin, Yucai Yang, Rong Xie, and Li Song^♯

   IEEE Transactions on Circuits and Systems for Video Technology, Jun 2025

   DOI

8. 

   Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration

   Yuhong Zhang, Hengsheng Zhang, Xinning Chai, Zhengxue Cheng^♯, Rong Xie, Li Song^♯, and Wenjun Zhang

   IEEE Transactions on Circuits and Systems for Video Technology, Jun 2025

   DOI

9. 

   SSP-IR: Semantic and Structure Priors for Diffusion-Based Realistic Image Restoration

   Yuhong Zhang, Hengsheng Zhang, Zhengxue Cheng^♯, Rong Xie, Li Song^♯, and Wenjun Zhang

   IEEE Transactions on Circuits and Systems for Video Technology, Jun 2025

   DOI

10. 

    OmniVTLA: Vision-Tactile-Language-Action Model with Semantic-Aligned Tactile Sensing

    Zhengxue Cheng, Yiqian Zhang, Wenkang Zhang, Haoyu Li, Keyu Wang, Li Song, and Hengdi Zhang

    Jun 2025

2024

1. 

   Rate-aware Compression for NeRF-based Volumetric Video

   Zhiyu Zhang^*, Guo Lu^*, Huanxiong Liang, Zhengxue Cheng^♯, Anni Tang, and Li Song^♯

   In Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne VIC, Australia, Jun 2024

   DOI

2020

1. 

   Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules

   Zhengxue Cheng, Heming Sun, Masaru Takeuchi, and Jiro Katto

   In , Jun 2020

   Abs PDF

   Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results. However, there is still a performance gap between learned compression algorithms and reigning compression standards, especially in terms of widely used PSNR metric. In this paper, we explore the remaining redundancy of recent learned compression algorithms. We have found accurate entropy models for rate estimation largely affect the optimization of network parameters and thus affect the rate-distortion performance. Therefore, in this paper, we propose to use discretized Gaussian Mixture Likelihoods to parameterize the distributions of latent codes, which can achieve a more accurate and flexible entropy model. Besides, we take advantage of recent attention modules and incorporate them into network architecture to enhance the performance. Experimental results demonstrate our proposed method achieves a state-of-the-art performance compared to existing learned compression methods on both Kodak and high-resolution datasets. To our knowledge our approach is the first work to achieve comparable performance with latest compression standard Versatile Video Coding (VVC) regarding PSNR. More importantly, our approach generates more visually pleasant results when optimized by MS-SSIM.

2. Energy Compaction-Based Image Compression Using Convolutional AutoEncoder

   Zhengxue Cheng, Heming Sun, Masaru Takeuchi, and Jiro Katto

   IEEE Transactions on Multimedia, Jun 2020

   Abs DOI

   Image compression has been an important research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and its use in image compression has gradually been increasing. In this paper, we present an energy compaction-based image compression architecture using a convolutional autoencoder (CAE) to achieve high coding efficiency. Our main contributions include three aspects: 1) we propose a CAE architecture for image compression by decomposing it into several down(up)sampling operations; 2) for our CAE architecture, we offer a mathematical analysis on the energy compaction property and we are the first work to propose a normalized coding gain metric in neural networks, which can act as a measurement of compression capability; 3) based on the coding gain metric, we propose an energy compaction-based bit allocation method, which adds a regularizer to the loss function during the training stage to help the CAE maximize the coding gain and achieve high compression efficiency. The experimental results demonstrate our proposed method outperforms BPG (HEVC-intra), in terms of the MS-SSIM quality metric. Additionally, we achieve better performance in comparison with existing bit allocation methods, and provide higher coding efficiency compared with state-of-the-art learning compression methods at high bit rates.

3. Learned Lossless Image Compression with A Hyperprior and Discretized Gaussian Mixture Likelihoods

   Zhengxue Cheng, Heming Sun, Masaru Takeuchi, and Jiro Katto

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2020

   DOI

2019

1. Learning Image and Video Compression Through Spatial-Temporal Energy Compaction

   Zhengxue Cheng, Heming Sun, Masaru Takeuchi, and Jiro Katto

   In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2019

   DOI