JYJiayu Yang

Jiayu Yang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jiayu Yang has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    DyGS-Dataset: A High-Fidelity and Temporal-stable Dynamic 3DGS Dataset

    by Xiang Li, Wenhui Song, Chao Wang, Jiayu Yang, Jiahao Wu, Jie Liang, Kaiqiang Xiong, Ronggang Wang

  • Open Access

    ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation

    by Jiahao Wu, Jie Liang, Die Hu, Jiayu Yang, Kaiqiang Xiong, Xiang Li, Xiaoyun Zheng, Chao Wang, Ronggang Wang

    Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose ATGS, a Gaussian splatting based framework for volumetric video reconstruction. Our key insight is that explicitly tracking long term complex motion with individual Gaussian primitives is inherently unstable. Instead, we organize Gaussians around time conditioned anchors that localize their spatial and temporal support, thereby reducing long range motion complexity. We further introduce a temporal windowing strategy to activate only anchors relevant to the queried time, which improves scalability and temporal coherence. In addition, to ensure spatial and temporal stability, we design a compact set of multi level anchor features that encode global features, local spatial features, and local temporal features, jointly constraining Gaussian generation. Extensive experiments demonstrate that ATGS consistently outperforms prior methods on long sequence volumetric videos with complex motions. Project page: https://github.com/WuJH2001/ATGS.

  • i3DV: Intelligent 3D Volumetric Video Coding Standard and Platform

    by Jiayu Yang, Luyang Tang, Jiahao Wu, Jie Liang, Feng Gao, Ronggang Wang

    3D volumetric video enables users to freely navigate and observe scenes from any position and view direction through interactive operations, delivering more authentic and immersive viewing experiences. To address the issues of 6DoF interaction, photorealistic rendering quality of virtual viewpoints and efficient compression, the Audio Video Coding Standard Workgroup of China (AVS) is developing an intelligent 3D volumetric video coding standard named i3DV. The standard proposes a paradigm shift for 3D volumetric video, taking the advantages of implicit differentiable representation models for intelligent volumetric video reconstruction and coding. This paper provides an overview of the technical features and characteristics of the i3DV standard. In addition, this paper provides a report on the primary efforts of the reference software platform and its coding efficiency. The exploration experiment shows that the platform achieves high-quality virtual viewpoint rendering while significantly compressing the data size of volumetric video.


  • Top Cited Papers
    Open Access

    MLICv2: Enhanced Multi-Reference Entropy Modeling for Learned Image Compression

    by Wei Jiang, Yongqi Zhai, Jiayu Yang, Feng Gao, Ronggang Wang

    Recent advances in Learned Image Compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series—LICs equipped with multi-reference entropy models—have substantially surpassed conventional image codecs such as Versatile Video Coding (VVC) Intra. However, existing MLIC variants suffer from several limitations: performance degradation at high bit-rates due to insufficient transform capacity, suboptimal entropy modeling that fails to capture global correlations in initial slices, and lack of adaptive channel importance modeling. In this article, we propose MLICv2 and MLICv2 \({}^{+}\) , enhanced successors that systematically address these limitations through improved transform design, advanced entropy modeling, and exploration of the potential of instance-specific optimization. For transform enhancement, we introduce a lightweight token mixing block inspired by the MetaFormer architecture, which effectively mitigates high-bit-rate performance degradation while maintaining computational efficiency. For entropy modeling improvements, we propose hyperprior-guided global correlation prediction to extract global context even in the initial slice of latent representation, complemented by a channel reweighting module that dynamically emphasizes informative channels. We further explore enhanced positional embedding and guided selective compression strategies for superior context modeling. Additionally, we apply the Stochastic Gumbel Annealing (SGA) to demonstrate the potential for further performance improvements through input-specific optimization. Extensive experiments demonstrate that MLICv2 and MLICv2 \({}^{+}\) achieve state-of-the-art results, reducing Bjøntegaard-Delta Rate by 16.54%, 21.61%, 16.05% and 20.46%, 24.35%, 19.14% on Kodak, Tecnick, and CLIC Pro Val datasets, respectively, compared to VTM-17.0 Intra.


  • Open Access

    Collaborative Optimization Scheduling of “Source-Grid-Load-Storage” in Zero-Carbon Parks Based on Dynamic Carbon Flow Tracking

    by Yun Xu, Xia Zong, Xiaojian Liu, Shuaishuai Ren, Jiayu Yang, Jian Gao, Pengfei Cheng, Xinxian Chen

    To achieve low-carbon and efficient operation of the energy system in the park, this paper proposes a “source-grid-load-storage” collaborative optimization scheduling method for zero-carbon parks based on dynamic carbon flow tracking. By establishing a dynamic carbon flow tracking model, the carbon intensity of nodes is calculated in real time to reveal the spatio-temporal distribution characteristics of the carbon flow in the system; Based on this, a collaborative optimization scheduling model aimed at economy and low carbon is constructed, taking into account power balance, equipment operation constraints and carbon constraints, and solved using the mixed integer linear programming method. The case analysis shows that the proposed method, while ensuring the reliable operation of the system, significantly enhances the capacity of renewable energy consumption, achieves the reduction of total operating costs and effective control of carbon emissions, and provides theoretical basis and technical support for the actual scheduling of zero-carbon parks.

  • Open Access

    Excavating the Most Critical Gaussians: Sparse Selection and Structural Optimization for Efficient 3DGS Compression

    by Yang Hu, Jingui Ma, Yucheng Yang, Jie Liang, Jinbo Yan, Jiahao Wu, Jiayu Yang, Yang Deng, Ronggang Wang


  • Top Cited Papers
    Open Access

    MLIC ++ : Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression

    by Wei Jiang, Jiayu Yang, Yongqi Zhai, Feng Gao, Ronggang Wang

    The latent representation in learned image compression encompasses channel-wise, local spatial, and global spatial correlations, which are essential for the entropy model to capture for conditional entropy minimization. Efficiently capturing these contexts within a single entropy model, especially in high-resolution image coding, presents a challenge due to the computational complexity of existing global context modules. To address this challenge, we propose the Linear Complexity Multi-Reference Entropy Model (MEM \({}^{++}\) ). Specifically, the latent representation is partitioned into multiple slices. For channel-wise contexts, previously compressed slices serve as the context for compressing a particular slice. For local contexts, we introduce a shifted-window-based checkerboard attention module. This module ensures linear complexity without sacrificing performance. For global contexts, we propose a linear complexity attention mechanism. It captures global correlations by decomposing the softmax operation, enabling the implicit computation of attention maps from previously decoded slices. Using MEM++ as the entropy model, we develop the image compression method MLIC \({}^{++}\) . Extensive experimental results demonstrate that MLIC \({}^{++}\) achieves state-of-the-art performance, reducing BD-rate by \(13.39\%\) on the Kodak dataset compared to VTM-17.0 in Peak Signal-to-Noise Ratio (PSNR). Furthermore, MLIC \({}^{++}\) exhibits linear computational complexity and memory consumption with resolution, making it highly suitable for high-resolution image coding. Code and pre-trained models are available at https://github.com/JiangWeibeta/MLIC .


  • Open Access

    Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting

    by Jinbo Yan, Rui Peng, Zhiyan Wang, Luyang Tang, Jiayu Yang, Jie Liang, Jiahao Wu, Ronggang Wang

    Building Free-Viewpoint Videos in a streaming manner offers the advantage of rapid responsiveness compared to offline training methods, greatly enhancing user experience. However, current streaming approaches face challenges of high per-frame reconstruction time (10s+) and error accumulation, limiting their broader application. In this paper, we propose Instant Gaussian Stream (IGS), a fast and generalizable streaming framework, to address these issues. First, we introduce a generalized Anchor-driven Gaussian Motion Network, which projects multi-view 2D motion features into 3D space, using anchor points to drive the motion of all Gaussians. This generalized Network generates the motion of Gaussians for each target frame in the time required for a single inference. Second, we propose a Key-frame-guided Streaming Strategy that refines each key frame, enabling accurate reconstruction of temporally complex scenes while mitigating error accumulation. We conducted extensive in-domain and cross-domain evaluations, demonstrating that our approach can achieve streaming with a average per-frame reconstruction time of 2s+, alongside a enhancement in view synthesis quality.


  • Open Access

    Adaptive Prediction Structure for Learned Video Compression

    by Jiayu Yang, Yongqi Zhai, Wei Jiang, Chunhui Yang, Feng Gao, Ronggang Wang

    Learned video compression has developed rapidly and shown competitive rate-distortion performance compared with the latest traditional video coding standard H.266 (VVC). However, existing works were restricted to fixed prediction direction and GoP size. The inflexibility on prediction structure hinders learned video compression towards optimal compression efficiency in diverse motion scenarios. In this article, we propose to advance learned video compression with adaptive prediction structure decision. Specifically, we propose a unified compression framework that supports both forward prediction and bi-directional prediction. The framework can flexibly switch to different prediction direction to achieve better prediction performance. Meanwhile, we propose a low-complexity prediction structure decision algorithm, where prediction direction and GoP size are adaptively determined based on motion complexity to achieve optimal compression efficiency. Experimental results demonstrate that the proposed unified framework with adaptive decision algorithm improves compression efficiency of pure forward prediction-based or bi-directional prediction-based framework with neglectable ( \(0.9\%\) ) encoding time increment. Meanwhile, it achieves comparable compression performance with VVC and recent learned video coding methods.


  • LLIC: Large Receptive Field Transform Coding With Adaptive Weights for Learned Image Compression

    by Wei Jiang, Peirong Ning, Jiayu Yang, Yongqi Zhai, Feng Gao, Ronggang Wang

    The effective receptive field (ERF) plays an important role in transform coding, which determines how much redundancy can be removed during transform and how many spatial priors can be utilized to synthesize textures during inverse transform. Existing methods rely on stacks of small kernels, whose ERFs remain insufficiently large, or heavy non-local attention mechanisms, which limit the potential of high-resolution image coding. To tackle this issue, we propose Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression (LLIC). Specifically, for the first time in the learned image compression community, we introduce a few large kernel-based depth-wise convolutions to reduce more redundancy while maintaining modest complexity. Due to the wide range of image diversity, we further propose a mechanism to augment convolution adaptability through the self-conditioned generation of weights. The large kernels cooperate with non-linear embedding and gate mechanisms for better expressiveness and lighter point-wise interactions. Our investigation extends to refined training methods that unlock the full potential of these large kernels. Moreover, to promote more dynamic inter-channel interactions, we introduce an adaptive channel-wise bit allocation strategy that autonomously generates channel importance factors in a self-conditioned manner. To demonstrate the effectiveness of the proposed transform coding, we align the entropy model to compare with existing transform methods and obtain models LLIC-STF, LLIC-ELIC, and LLIC-TCM. Extensive experiments demonstrate that our proposed LLIC models have significant improvements over the corresponding baselines and reduce the BD-Rate by $9.49\%, 9.47\%, 10.94\%$ on Kodak over VTM-17.0 Intra, respectively. Our LLIC models achieve state-of-the-art performances and better trade-offs between performance and complexity.