HMHengyu Man

Hengyu Man

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hengyu Man has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting

    by Xuan Deng, Hengyu Man, Qiang Zhu, Xiandong Meng, Tiange Zhang, Debin Zhao, Xiaopeng Fan

    Although 3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, its prohibitive storage overhead hinders practical deployment. Recent anchor-based 3DGS compression schemes reduce Gaussian redundancy through advanced context models. However, they overlook explicit local geometric dependencies among neighboring anchors, leading to structural degradation and suboptimal rate-distortion performance.In this paper, we propose a Local Geometry-aware Hierarchical Context Compression (LG-HCC) framework for 3DGS that incorporates inter-anchor geometric correlations into both anchor pruning and entropy coding. Specifically, we introduce Neighborhood-aware Anchor Pruning (NAP), which evaluates anchor importance via weighted neighborhood aggregation and merges low-contribution anchors into salient neighbors to preserve local geometric structure cues. Moreover, we develop a hierarchical entropy coding scheme, where coarse-to-fine priors are refined by a lightweight Geometry-Guided Convolution (GG-Conv) that aggregates local geometric context for spatially adaptive probability estimation. Extensive experiments show that LG-HCC improves geometric consistency and rendering fidelity while reducing storage by up to 30.85$\times$ compared with Scaffold-GS on Mip-NeRF360.

  • LNeRV: Disentangled Latent Representation for Semantic-Aware Video Dynamics Modeling

    by Yan Shen, Hengyu Man, Wenxue Cui, Wangmeng Zuo, Xiaopeng Fan, Debin Zhao

    Implicit Neural Representations (INRs) have emerged as a promising paradigm for video coding by enabling continuous signal modeling through coordinate-based neural networks. However, existing video INR methods often model temporal variation either in the pixel domain or with a single dynamic code, which limits their ability to jointly preserve rapidly varying high-frequency details and long-range semantic motion patterns. To address this issue, we propose the Latent-disentangled Neural Representation for Videos (LNeRV), a framework that models video dynamics in latent space using dual dynamic feature grids. Specifically, a denser high-resolution grid is used to capture short-term detail dynamics, while a coarser low-rate grid is used to capture long-range semantic motion patterns. On top of these complementary grids, we introduce a Clustering-based Context Aggregation (CCA) module to combine short-term motion details with long-range temporal context, and a Decoupled Gated Attention (DGA) module as a lightweight gated fusion mechanism to enlarge the receptive field during feature interaction. Extensive experiments demonstrate that LNeRV achieves state-of-the-art video regression performance on the UVG dataset under both PSNR and MS-SSIM metrics. Compared with vanilla NeRV, LNeRV achieves an average PSNR gain of 2.52 dB on UVG, while also showing strong structural fidelity in the compressed rate-distortion setting.


  • DV-Hop Localization Based on Probability Distance Estimation and Expected Hop Distance Correction

    by Penghong Wang, Hao Wang, Wenrui Li, Hengyu Man, Xin Yue, Xiaopeng Fan, Debin Zhao

    Distance estimation and theoretical derivation in 3D space form the foundation basis for improving localization performance in wireless sensor networks (WSNs). Localization is a pivotal challenge in wireless sensor network (WSN) applications. To address this issue, we propose a probability-based distance estimation (PDE) model and a distance correction strategy based on expected hops (DCSEH). First, the PDE model is constructed from the multi-hop probability distribution of nodes, from which the upper bound and average distance for anchor nodes to detect target nodes under different hop counts are derived. Second, the DCSEH strategy effectively mitigates transmission-path detours in wireless node communication. Finally, the constructed loss function is embedded into a multi-objective genetic algorithm to predict the position of each unknown node in three-dimensional space. Extensive experiments demonstrate that the proposed method achieves state-of-the-art 3D localization performance on both random and multimodal datasets.

  • Learned Reference Picture Resampling Control: A Data-Centric Approach

    by Riyu Lu, Yingwen Zhang, Hengyu Man, Meng Wang, Long Xu, Shiqi Wang, Xiaopeng Fan

    Learned reference picture resampling control (LRPRC) adaptively adjusts the coding scale for each frame using an offline-trained neural network. It demonstrates promising promising rate-distortion (R-D) performance improvements over traditional methods, particularly in high-resolution, low-bit-rate video coding scenarios. However, existing LRPRC methods rely exclusively on locally optimal decision labels derived from greedy strategies for network training, leading to suboptimal control performance. To address this limitation, we introduce a novel data-centric solution that substantially improves training label quality, thereby enhancing overall LRPRC performance. Specifically, our key contribution is a parallelized beam search-based coding scale labeling algorithm, which captures decision dependencies across coding steps and produces higher-quality training labels with enhanced R-D performance. By fully exploiting the intra-trellis and inter-trellis parallelism of beam search and hierarchical coding, our proposed labeling algorithm achieves logarithmic-squared time complexity, making it highly suitable for large-scale cluster computing. We validate this simple yet effective data-centric LRPRC approach in the Versatile Video Encoder (VVenC) using 4K video sequences. Experimental results demonstrate that merely upgrading the beam search labels (without any neural architecture re-designs) consistently outperforms the state-of-the-art LRPRC method, achieving BD-rate reductions of 5.09%, 3.98%, and 3.59% under the fast, medium, and slow presets, respectively.


  • Language-Guided Graph Representation Learning for Video Summarization

    by Wenrui Li, Wei Han, Hengyu Man, Wangmeng Zuo, Xiaopeng Fan, Yonghong Tian

    With the rapid growth of video content on social media, video summarization has become a crucial task in multimedia processing. However, existing methods face challenges in capturing global dependencies in video content and accommodating multimodal user customization. Moreover, temporal proximity between video frames does not always correspond to semantic proximity. To tackle these challenges, we propose a novel Language-guided Graph Representation Learning Network (LGRLN) for video summarization. Specifically, we introduce a video graph generator that converts video frames into a structured graph to preserve temporal order and contextual dependencies. By constructing forward, backward and undirected graphs, the video graph generator effectively preserves the sequentiality and contextual relationships of video content. We designed an intra-graph relational reasoning module with a dual-threshold graph convolution mechanism, which distinguishes semantically relevant frames from irrelevant ones between nodes. Additionally, our proposed language-guided cross-modal embedding module generates video summaries with specific textual descriptions. We model the summary generation output as a mixture of Bernoulli distribution and solve it with the EM algorithm. Experimental results show that our method outperforms existing approaches across multiple benchmarks. Moreover, we proposed LGRLN reduces inference time and model parameters by 87.8% and 91.7%, respectively.


  • Open Access

    Hyperbolic Hierarchical Alignment Reasoning Network for Text-3D Retrieval

    by Wenrui Li, Yidan Lu, Yeyu Chai, Rui Zhao, Hengyu Man, Xiaopeng Fan

    With the daily influx of 3D data on the internet, text-3D retrieval has gained increasing attention. However, current methods face two major challenges: Hierarchy Representation Collapse (HRC) and Redundancy-Induced Saliency Dilution (RISD). HRC compresses abstract-to-specific and whole-to-part hierarchies in Euclidean embeddings, while RISD averages noisy fragments, obscuring critical semantic cues and diminishing the model's ability to distinguish hard negatives. To address these challenges, we introduce the Hyperbolic Hierarchical Alignment Reasoning Network (H$^{2}$ARN) for text-3D retrieval. H$^{2}$ARN embeds both text and 3D data in a Lorentz-model hyperbolic space, where exponential volume growth inherently preserves hierarchical distances. A hierarchical ordering loss constructs a shrinking entailment cone around each text vector, ensuring that the matched 3D instance falls within the cone, while an instance-level contrastive loss jointly enforces separation from non-matching samples. To tackle RISD, we propose a contribution-aware hyperbolic aggregation module that leverages Lorentzian distance to assess the relevance of each local feature and applies contribution-weighted aggregation guided by hyperbolic geometry, enhancing discriminative regions while suppressing redundancy without additional supervision. We also release the expanded T3DR-HIT v2 benchmark, which contains 8,935 text-to-3D pairs, 2.6 times the original size, covering both fine-grained cultural artefacts and complex indoor scenes. Our codes are available at https://github.com/liwrui/H2ARN.

  • Mining Temporal Priors for Template-Generated Video Compression

    by Feng Xing, Yingwen Zhang, Meng Wang, Hengyu Man, Yongbing Zhang, Shiqi Wang, Xiaopeng Fan, Wen Gao

    The popularity of template-generated videos has recently experienced a significant increase on social media platforms. In general, videos from the same template share similar temporal characteristics, which are unfortunately ignored in the current compression schemes. In view of this, we aim to examine how such temporal priors from templates can be effectively utilized during the compression process for template-generated videos. First, a comprehensive statistical analysis is conducted, revealing that the coding decisions, including the merge, non-affine, and motion information, across template-generated videos are strongly correlated. Subsequently, leveraging such correlations as prior knowledge, a simple yet effective prior-driven compression scheme for template-generated videos is proposed. In particular, a mode decision pruning algorithm is devised to dynamically skip unnecessarily advanced motion vector prediction (AMVP) or affine AMVP decisions. Moreover, an improved AMVP motion estimation algorithm is applied to further accelerate reference frame selection and the motion estimation process. Experimental results on the versatile video coding (VVC) platform VTM-23.0 demonstrate that the proposed scheme achieves moderate time reductions of 14.31% and 14.99% under the Low-Delay P (LDP) and Low-Delay B (LDB) configurations, respectively, while maintaining negligible increases in Bjøntegaard Delta Rate (BD-Rate) of 0.15% and 0.18%, respectively.

  • Open Access

    Hyperbolic-Constraint Point Cloud Reconstruction from Single RGB-D Images

    by Wenrui Li, Zhe Yang, Wei Han, Hengyu Man, Xingtao Wang, Xiaopeng Fan

    Reconstructing desired objects and scenes has long been a primary goal in 3D computer vision. Single-view point cloud reconstruction has become a popular technique due to its low cost and accurate results. However, single-view reconstruction methods often rely on expensive CAD models and complex geometric priors. Effectively utilizing prior knowledge about the data remains a challenge. In this paper, we introduce hyperbolic space to 3D point cloud reconstruction, enabling the model to represent and understand complex hierarchical structures in point clouds with low distortion. We build upon previous methods by proposing a hyperbolic Chamfer distance and a regularized triplet loss to enhance the relationship between partial and complete point clouds. Additionally, we design adaptive boundary conditions to improve the model's understanding and reconstruction of 3D structures. Our model outperforms most existing models, and ablation studies demonstrate the significance of our model and its components. Experimental results show that our method significantly improves feature extraction capabilities. Our model achieves outstanding performance in 3D reconstruction tasks.


  • Learning the Scale in Reference Picture Resampling for Versatile Video Coding

    by Riyu Lu, Yingwen Zhang, Hengyu Man, Meng Wang, Shiqi Wang, Xiaopeng Fan

    Compressing high-resolution videos under low bitrate constraints is a challenging task. Resampling-based compression, which reduces the resolution before encoding and restores it after decoding, has great potential to improve the rate-distortion performance in such scenarios. In this paper, we propose a learning-based frame-level coding scale control scheme that enhances the coding performance by adjusting the coding scale for each frame. The scheme cooperates with the Reference Picture Resampling of the latest video coding standard Versatile Video Coding (VVC), which allows coding scale variations on each frame. More specifically, a dataset with 5200 videos is created by a greedy rate-distortion optimization algorithm employed to select the optimal coding scale for each frame. A neural network-based decision model is further incorporated into VVC, learning to predict the coding scale for each frame in one pass. The scheme is implemented into the Fraunhofer Versatile Video Encoder (VVenC), a fast and efficient VVC encoder, and evaluated on 4K contents. Experimental results show that the proposed scheme outperforms GOP-based coding scale adaptation methods, achieving average bitrate savings of 3.06% and 4.14% in terms of PSNR and MS-SSIM.


  • Content-Aware Dynamic In-Loop Filter With Adjustable Complexity for VVC Intra Coding

    by Hengyu Man, Hao Wang, Riyu Lu, Zhaolin Wan, Xiaopeng Fan, Debin Zhao

    Recently, neural network-based in-loop filters have been rapidly developed, effectively improving the reconstruction quality and compression efficiency in video coding. Existing deep in-loop filters typically employed networks with fixed structures to process all image blocks. However, under various bitrate conditions, compressed image blocks with different textures exhibit varying degradations, which poses a challenge for high-quality and low-complexity filtering. Additionally, different complexity requirements for coding tools in various scenarios limit the versatility of fixed models. To address these problems, a content-aware dynamic in-loop filter (dubbed DILF) with adjustable complexity is proposed in this paper. Specifically, DILF comprises a policy network and a filtering network. For each reconstructed image block, the policy network dynamically generates a filtering network topology based on pixel information and the quantization parameter (QP), guiding the filtering network to skip redundant layers and conduct content-aware image enhancement, thereby improving the filtering performance. In addition, by introducing a user-defined balancing factor into the policy network, the content-aware filtering network topology can be further adjusted according to user’s requirements, facilitating adjustable complexity with a single model. We integrate DILF into Versatile Video Coding (VVC) to replace the built-in deblocking filter. Extensive experiments demonstrate the efficiency of DILF in processing image blocks with varying degrees of degradation and its flexibility in controlling complexity. When the balancing factor is set to 2e-5, DILF achieves bitrate savings of 8.07%, 17.97%, and 20.93% on average for YUV components over VVC reference software VTM-11.0 under all-intra configuration. Compared to static networks with fixed structures, DILF demonstrates superior performance and lower computational complexity.