This paper proposes an efficient 3D avatar coding framework that leverages compact human priors and canonical-to-target transformation to enable high-quality 3D human avatar video compression at ultra-low bit rates. The framework begins by training a canonical Gaussian avatar using articulated splatting in a network-free manner, which serves as the foundation for avatar appearance modeling. Simultaneously, a human-prior template is employed to capture temporal body movements through compact parametric representations. This decomposition of appearance and temporal evolution minimizes redundancy, enabling efficient compression: the canonical avatar is shared across the sequence, requiring compression only once, while the temporal parameters, consisting of just 94 parameters per frame, are transmitted with minimal bit-rate. For each frame, the target human avatar is generated by deforming canonical avatar via Linear Blend Skinning transformation, facilitating temporalcoherent video reconstruction and novel view synthesis. Experimental results demonstrate that the proposed method significantly outperforms conventional 2D/3D codecs and existing learnable dynamic 3D Gaussian splatting compression method in terms of rate-distortion performance on mainstream multi-view human video datasets, paving the way for seamless immersive multimedia experiences in meta-verse applications.

Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in real-world applications. Herein, we propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size. To ensure the compactness of Gaussian primitives, we devise a hybrid primitive structure that captures predictive relationships between each other. Then, we exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms. Moreover, we develop a rate-constrained optimization scheme to eliminate redundancies within such hybrid primitives, steering our CompGS towards an optimal trade-off between bitrate consumption and representation efficacy. Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality. Our code will be released on GitHub for further research.

The emergence of digital avatars has prompted an exponential increase in the demand for human point clouds with realistic and intricate details. The compression of such data becomes challenging due to massive amounts of data comprising millions of points. Herein, we leverage the human geometric prior in the geometry redundancy removal of point clouds to greatly promote compression performance. More specifically, the prior provides topological constraints as geometry initialization, allowing adaptive adjustments with a compact parameter set that can be represented with only a few bits. Therefore, we propose representing high-resolution human point clouds as a combination of a geometric prior and structural deviations. The prior is first derived with an aligned point cloud. Subsequently, the difference in features is compressed into a compact latent code. The proposed framework can operate in a plug-and-play fashion with existing learning-based point cloud compression methods. Extensive experimental results show that our approach significantly improves the compression performance without deteriorating the quality, demonstrating its promise in serving a variety of applications.

In this paper, we focus on subjective and objective Point Cloud Quality Assessment (PCQA) in an immersive environment and study the effect of geometry and texture attributes in compression distortion. Using a Head-Mounted Display (HMD) with six degrees of freedom, we establish a subjective PCQA database, named SIAT Point Cloud Quality Database (SIAT-PCQD). Our database consists of 340 distorted point clouds compressed by the MPEG point cloud encoder with the combination of 20 sequences and 17 pairs of geometry and texture quantization parameters. The impact of distorted geometry and texture attributes is further discussed in this paper. Then, we propose two projection-based objective quality evaluation methods, i.e., a weighted view projection based model and a patch projection based model. Our subjective database and findings can be used in point cloud processing, transmission, and coding, especially for virtual reality applications. The subjective datasethttps://dx.doi.org/10.21227/ad8d-7r28http://codec.siat.ac.cn/video_download_siat-pcqd.htmlhasbeen released in the public repository.

Omnidirectional video is required to be projected from the Three-Dimensional (3D) sphere to a Two-Dimensional (2D) plane before compression due to its spherical characteristics. Therefore, various projection formats have been proposed in recent years. However, these existing projection methods have problems of either oversampling or discontinuous boundary, which penalize the coding performance. Among them, Hybrid Equiangular Cubemap (HEC) projection has achieved significant coding gains by keeping boundary continuity when compared with Equi-Angular Cubemap (EAC) projection. However, the parameters of its mapping function are fixed and cannot adapt to the video contents, which results in non-uniform sampling in certain regions. To address this limitation, a projection method named Content-aware HEC (CHEC) is presented in this paper. In particular, these parameters of mapping function are adaptively achieved by minimizing the projection conversion distortion. Additionally, an omnidirectional video coding framework with adaptive parameters of mapping function is proposed to effectively improve the coding performance. Experimental results show that the proposed scheme achieves 8.57% and 0.11% bit rate reduction on average in terms of End-to-End Weighted to Spherically uniform Peak Signal to Noise Ratio (E2E WS-PSNR) when compared with Equi-Rectangular Projection (ERP) and HEC projections, respectively.

In this paper, a novel intra prediction method is presented for lossless/near lossless High Efficiency Video Coding (HEVC), termed as Sparse Representation based Intra Prediction (SRIP). In specific, the existing Angular Intra Prediction (AIP) modes in HEVC are organized as a mode dictionary, which is utilized to sparsely represent the visual signal by minimizing the difference with respect to the ground truth. For the match of encoding and decoding, the sparse coefficients are also required to be encoded and transmitted to the decoder side. To further improve the coding performance, an additional binary flag is included in the video codec to indicate which strategy is finally adopted with the rate distortion optimization, i.e., SRIP or traditional AIP. Extensive experimental results reveal that the proposed method can achieve 0.36% bit rate saving on average in case of lossless scenario.