Fei Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fei Song has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Wei Gao
School of Electronic and Computer Engineering, Peking University, Shenzhen, China
4 shared publications - Ge Li
Shenzhen Graduate School, Peking University, Shenzhen, China
3 shared publications - Shan Liu
Sichuan Provincial Key Laboratory for Human Disease Gene Study, Department of Medical Genetics, Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, 610072, China
2 shared publications - Yiting Shao
School of Hydraulic Engineering, Zhejiang University of Water Resources and Electric Power, Hangzhou 310018, China
2 shared publications - Haiqiang Wang
University of Southern California, Los Angeles, USA
1 shared publication Thomas H. Li
AIIT, Peking University, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 11 May 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (10) , 4094
Texture-Guided Graph Transform Optimization for Point Cloud Attribute Compression
There is a pressing need across various applications for efficiently compressing point clouds. While the Moving Picture Experts Group introduced the geometry-based point cloud compression (G-PCC) standard, its attribute compression scheme falls short of eliminating signal frequency-domain redundancy. This paper proposes a texture-guided graph transform optimization scheme for point cloud attribute compression. We formulate the attribute transform coding task as a graph optimization problem, considering both the decorrelation capability of the graph transform and the sparsity of the optimized graph within a tailored joint optimization framework. First, the point cloud is reorganized and segmented into local clusters using a Hilbert-based scheme, enhancing spatial correlation preservation. Second, the inter-cluster attribute prediction and intra-cluster prediction are conducted on local clusters to remove spatial redundancy and extract texture priors. Third, the underlying graph structure in each cluster is constructed in a joint rate–distortion–sparsity optimization process, guided by geometry structure and texture priors to achieve optimal coding performance. Finally, point cloud attributes are efficiently compressed with the optimized graph transform. Experimental results show the proposed scheme outperforms the state of the art with significant BD-BR gains, surpassing G-PCC by 31.02%, 30.71%, and 32.14% in BD-BR gains for Y, U, and V components, respectively. Subjective evaluation of the attribute reconstruction quality further validates the superiority of our scheme.
- 11 May 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (10) , 4094
Open AccessTexture-Guided Graph Transform Optimization for Point Cloud Attribute Compression
There is a pressing need across various applications for efficiently compressing point clouds. While the Moving Picture Experts Group introduced the geometry-based point cloud compression (G-PCC) standard, its attribute compression scheme falls short of eliminating signal frequency-domain redundancy. This paper proposes a texture-guided graph transform optimization scheme for point cloud attribute compression. We formulate the attribute transform coding task as a graph optimization problem, considering both the decorrelation capability of the graph transform and the sparsity of the optimized graph within a tailored joint optimization framework. First, the point cloud is reorganized and segmented into local clusters using a Hilbert-based scheme, enhancing spatial correlation preservation. Second, the inter-cluster attribute prediction and intra-cluster prediction are conducted on local clusters to remove spatial redundancy and extract texture priors. Third, the underlying graph structure in each cluster is constructed in a joint rate–distortion–sparsity optimization process, guided by geometry structure and texture priors to achieve optimal coding performance. Finally, point cloud attributes are efficiently compressed with the optimized graph transform. Experimental results show the proposed scheme outperforms the state of the art with significant BD-BR gains, surpassing G-PCC by 31.02%, 30.71%, and 32.14% in BD-BR gains for Y, U, and V components, respectively. Subjective evaluation of the attribute reconstruction quality further validates the superiority of our scheme.
- 10 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (8) , 4294-4308
Block-Adaptive Point Cloud Attribute Coding With Region-Aware Optimized Transform
Block-based compression scheme shows remarkable success in image and video coding. However, existing tree-type block partition methods usually divide point clouds into clusters with few or disjoint points due to the irregular sampling, which is adverse for the subsequent transform to exploit the local region correlation. Moreover, the widely-used optimal transform, e.g., Discrete Cosine Transform (DCT), is deduced with the assumption of the specified probability model. Thus these transforms cannot adequately conform to diverse statistical characteristics of point cloud attributes. To address the above two problems, we propose a block-adaptive codec with the optimized transform for point cloud attribute compression, including Progressive Clustering (PC) for block partition and Region-Aware Signal Modeling (RASM) for transform. PC is designed via the split-and-merge strategy. In the splitting phase, over-segmented clusters are obtained by iteratively searching the nearest neighbors to maintain the spatial continuity of points in one cluster. In the merging step, blocks are determined by merging over-segmented clusters under the guidance of minimizing texture complexity, which adjusts block sizes to adapt to texture variation. RASM adaptively captures the color correlations to respond to diverse statistical characteristics by optimizing the overall Rate-Distortion (RD) cost. Then, the optimal transform bases are obtained via the eigen-decomposition of the color correlation representation with respect to the Gaussian Markov Random Field, where input colors are obtained considering the linear relationship between geometry and color variations. The linear coefficients also need to be encoded to combine geometry to reconstruct the transform bases at the decoder in the same way as the encoder. Particularly, we accelerate the RASM by constraining the independent relationship between signals in the local region, which hardly influences RD performance. Extensive experiments not only indicate the effectiveness of PC and RASM but also show the significant RD gains achieved by our approach compared with several state-of-the-art platforms.
- 10 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (8) , 4294-4308
Block-Adaptive Point Cloud Attribute Coding With Region-Aware Optimized Transform
Block-based compression scheme shows remarkable success in image and video coding. However, existing tree-type block partition methods usually divide point clouds into clusters with few or disjoint points due to the irregular sampling, which is adverse for the subsequent transform to exploit the local region correlation. Moreover, the widely-used optimal transform, e.g., Discrete Cosine Transform (DCT), is deduced with the assumption of the specified probability model. Thus these transforms cannot adequately conform to diverse statistical characteristics of point cloud attributes. To address the above two problems, we propose a block-adaptive codec with the optimized transform for point cloud attribute compression, including Progressive Clustering (PC) for block partition and Region-Aware Signal Modeling (RASM) for transform. PC is designed via the split-and-merge strategy. In the splitting phase, over-segmented clusters are obtained by iteratively searching the nearest neighbors to maintain the spatial continuity of points in one cluster. In the merging step, blocks are determined by merging over-segmented clusters under the guidance of minimizing texture complexity, which adjusts block sizes to adapt to texture variation. RASM adaptively captures the color correlations to respond to diverse statistical characteristics by optimizing the overall Rate-Distortion (RD) cost. Then, the optimal transform bases are obtained via the eigen-decomposition of the color correlation representation with respect to the Gaussian Markov Random Field, where input colors are obtained considering the linear relationship between geometry and color variations. The linear coefficients also need to be encoded to combine geometry to reconstruct the transform bases at the decoder in the same way as the encoder. Particularly, we accelerate the RASM by constraining the independent relationship between signals in the local region, which hardly influences RD performance. Extensive experiments not only indicate the effectiveness of PC and RASM but also show the significant RD gains achieved by our approach compared with several state-of-the-art platforms.
- 23 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 29 (10709908) , 922-926
Rate-Distortion Optimized Graph for Point Cloud Attribute Coding
Recent years have witnessed remarkable success of Graph Fourier Transform (GFT) in point cloud attribute compression. Existing researches mainly utilize geometry distance to define graph structure for coding attribute (e.g., color), which may distribute high weights to the edges connecting points across texture boundaries. In this case, these geometry-based graphs cannot model attribute differences between points adequately, thus limiting the compression efficiency of GFT. Hence, we firstly utilize attribute itself to refine the distance-based weight values by setting penalty function, which smoothens signal variations on graph and concentrates more energies in the low frequencies. Then, adjacency matrices acting as penalty function variables are transmitted to decoder with extra bit overheads. To balance the attribute smoothness on graph and the cost of coding adjacency matrices, we finally propose the graph based on Rate-Distortion (RD) optimization and find the optimal adjacency matrix. Experimental results show that our algorithm improves RD performance compared with competitive platforms. Moreover, additional experiments also analyze the gain source by evaluating the effectiveness of RD optimized graphs.
- 23 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 29 (10709908) , 922-926
Rate-Distortion Optimized Graph for Point Cloud Attribute Coding
Recent years have witnessed remarkable success of Graph Fourier Transform (GFT) in point cloud attribute compression. Existing researches mainly utilize geometry distance to define graph structure for coding attribute (e.g., color), which may distribute high weights to the edges connecting points across texture boundaries. In this case, these geometry-based graphs cannot model attribute differences between points adequately, thus limiting the compression efficiency of GFT. Hence, we firstly utilize attribute itself to refine the distance-based weight values by setting penalty function, which smoothens signal variations on graph and concentrates more energies in the low frequencies. Then, adjacency matrices acting as penalty function variables are transmitted to decoder with extra bit overheads. To balance the attribute smoothness on graph and the cost of coding adjacency matrices, we finally propose the graph based on Rate-Distortion (RD) optimization and find the optimal adjacency matrix. Experimental results show that our algorithm improves RD performance compared with competitive platforms. Moreover, additional experiments also analyze the gain source by evaluating the effectiveness of RD optimized graphs.
- 21 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31 (12) , 4603-4616
Layer-Wise Geometry Aggregation Framework for Lossless LiDAR Point Cloud Compression
Point cloud compression is critical to deploy 3D applications like autonomous driving. However, LiDAR point clouds contain many disconnected regions, where redundant bits for unoccupied 3D space and weak correlations between points make it a troublesome problem to achieve efficient compression. This paper aims to aggregate LiDAR point clouds to get compact representations with full consideration of the point distribution characteristics. Specifically, we propose a novel Layer-wise Geometry Aggregation (LGA) framework for LiDAR point cloud lossless geometry compression, which adaptively partitions point clouds into three layers based on the content properties, including a ground layer, an object layer, and a noise layer. The aggregation algorithms are delicately designed for each layer. Firstly, the ground layer is fitted to a Gaussian Mixture Model, which can uniformly represent ground points using much fewer model parameters than adopting the original 3D coordinates. Then, the object layer is tightly packed to reduce the space between objects effectively, and a dense layout for points can benefit compression efficiency. Finally, in the noise layer, the difference between neighbor points is reduced by reordering using Morton Code, and the reduced residuals can help saving bit consumption. Experimental results demonstrate that the proposed LGA significantly outperforms competitive methods without prior knowledge by 12.05~23.37% compression ratio gains. Furthermore, the enhanced LGA with prior knowledge shows consistent performance gains than the latest reference software. Additional results also validate the robustness and stability of our proposed scheme with acceptable time complexity.
- 21 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31 (12) , 4603-4616
Layer-Wise Geometry Aggregation Framework for Lossless LiDAR Point Cloud Compression
Point cloud compression is critical to deploy 3D applications like autonomous driving. However, LiDAR point clouds contain many disconnected regions, where redundant bits for unoccupied 3D space and weak correlations between points make it a troublesome problem to achieve efficient compression. This paper aims to aggregate LiDAR point clouds to get compact representations with full consideration of the point distribution characteristics. Specifically, we propose a novel Layer-wise Geometry Aggregation (LGA) framework for LiDAR point cloud lossless geometry compression, which adaptively partitions point clouds into three layers based on the content properties, including a ground layer, an object layer, and a noise layer. The aggregation algorithms are delicately designed for each layer. Firstly, the ground layer is fitted to a Gaussian Mixture Model, which can uniformly represent ground points using much fewer model parameters than adopting the original 3D coordinates. Then, the object layer is tightly packed to reduce the space between objects effectively, and a dense layout for points can benefit compression efficiency. Finally, in the noise layer, the difference between neighbor points is reduced by reordering using Morton Code, and the reduced residuals can help saving bit consumption. Experimental results demonstrate that the proposed LGA significantly outperforms competitive methods without prior knowledge by 12.05~23.37% compression ratio gains. Furthermore, the enhanced LGA with prior knowledge shows consistent performance gains than the latest reference software. Additional results also validate the robustness and stability of our proposed scheme with acceptable time complexity.