Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911245619167232 |
|---|---|
| author | Deng, Xuan Wang, Xingtao Meng, Xiandong Wang, Longguang Zhang, Tiange Fan, Xiaopeng Zhao, Debin |
| author_facet | Deng, Xuan Wang, Xingtao Meng, Xiandong Wang, Longguang Zhang, Tiange Fan, Xiaopeng Zhao, Debin |
| contents | Efficient dynamic point cloud compression (DPCC) critically depends on accurate motion estimation and compensation. However, the inherently irregular structure and substantial local variations of point clouds make this task highly challenging. Existing approaches typically rely on explicit motion estimation, whose encoded motion vectors often fail to capture complex dynamics and inadequately exploit temporal correlations. To address these limitations, we propose a Bidirectional Feature-aligned Motion Transformation (Bi-FMT) framework that implicitly models motion in the feature space. Bi-FMT aligns features across both past and future frames to produce temporally consistent latent representations, which serve as predictive context in a conditional coding pipeline, forming a unified ``Motion + Conditional'' representation. Built upon this bidirectional feature alignment, we introduce a Cross-Transformer Refinement module (CTR) at the decoder side to adaptively refine locally aligned features. By modeling cross-frame dependencies with vector attention, CRT enhances local consistency and restores fine-grained spatial details that are often lost during motion alignment. Moreover, we design a Random Access (RA) reference strategy that treats the bidirectionally aligned features as conditional context, enabling frame-level parallel compression and eliminating the sequential encoding. Extensive experiments demonstrate that Bi-FMT surpasses D-DPCC and AdaDPCC in both compression efficiency and runtime, achieving BD-Rate reductions of 20% (D1) and 9.4% (D1), respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14591 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression Deng, Xuan Wang, Xingtao Meng, Xiandong Wang, Longguang Zhang, Tiange Fan, Xiaopeng Zhao, Debin Computer Vision and Pattern Recognition Efficient dynamic point cloud compression (DPCC) critically depends on accurate motion estimation and compensation. However, the inherently irregular structure and substantial local variations of point clouds make this task highly challenging. Existing approaches typically rely on explicit motion estimation, whose encoded motion vectors often fail to capture complex dynamics and inadequately exploit temporal correlations. To address these limitations, we propose a Bidirectional Feature-aligned Motion Transformation (Bi-FMT) framework that implicitly models motion in the feature space. Bi-FMT aligns features across both past and future frames to produce temporally consistent latent representations, which serve as predictive context in a conditional coding pipeline, forming a unified ``Motion + Conditional'' representation. Built upon this bidirectional feature alignment, we introduce a Cross-Transformer Refinement module (CTR) at the decoder side to adaptively refine locally aligned features. By modeling cross-frame dependencies with vector attention, CRT enhances local consistency and restores fine-grained spatial details that are often lost during motion alignment. Moreover, we design a Random Access (RA) reference strategy that treats the bidirectionally aligned features as conditional context, enabling frame-level parallel compression and eliminating the sequential encoding. Extensive experiments demonstrate that Bi-FMT surpasses D-DPCC and AdaDPCC in both compression efficiency and runtime, achieving BD-Rate reductions of 20% (D1) and 9.4% (D1), respectively. |
| title | Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.14591 |