Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.07346 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918489266061312 |
|---|---|
| author | Zhang, Haotian Mo, Xu Yu, Yixin Zhu, Guanhua Xue, Jian Xu, Tongda Wang, Yan Zhang, Jiaqi Ma, Siwei Gao, Wen |
| author_facet | Zhang, Haotian Mo, Xu Yu, Yixin Zhu, Guanhua Xue, Jian Xu, Tongda Wang, Yan Zhang, Jiaqi Ma, Siwei Gao, Wen |
| contents | Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods primarily focus on short video sequences and suffer from significant performance degradation when processing long-horizon free-viewpoint video (LFVV). Motivated by bit allocation theory, we analyze dynamic-anchor-based volumetric video representation within a rate-distortion optimization framework and propose \textbf{SoLAR}, which is the first error-resilient streamable FVV framework that maintains stable reconstruction quality on long sequences without requiring group-of-pictures partitioning. We propose the Anchor Activation Dynamics (AAD), which enables dynamic anchors to model non-rigid transformations by dynamically activating informative anchors and suppressing redundant ones. Furthermore, we introduce Latent Discrepancy Aware Recalibration (LaDAR), which is a mechanism to identify discrepancies between latent representations and recalibrate the correspondences encoded in the network, effectively mitigating error propagation in LFVV without compromising real-time performance or storage compactness. Extensive experiments demonstrate that \textbf{SoLAR} achieves state-of-the-art reconstruction performance while maintaining minimum storage overhead, which provides a new direction for LFVV reconstruction and advances the practical deployment of immersive systems. Demo free-viewpoint videos are provided in the supplementary material. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07346 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration Zhang, Haotian Mo, Xu Yu, Yixin Zhu, Guanhua Xue, Jian Xu, Tongda Wang, Yan Zhang, Jiaqi Ma, Siwei Gao, Wen Computer Vision and Pattern Recognition Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods primarily focus on short video sequences and suffer from significant performance degradation when processing long-horizon free-viewpoint video (LFVV). Motivated by bit allocation theory, we analyze dynamic-anchor-based volumetric video representation within a rate-distortion optimization framework and propose \textbf{SoLAR}, which is the first error-resilient streamable FVV framework that maintains stable reconstruction quality on long sequences without requiring group-of-pictures partitioning. We propose the Anchor Activation Dynamics (AAD), which enables dynamic anchors to model non-rigid transformations by dynamically activating informative anchors and suppressing redundant ones. Furthermore, we introduce Latent Discrepancy Aware Recalibration (LaDAR), which is a mechanism to identify discrepancies between latent representations and recalibrate the correspondences encoded in the network, effectively mitigating error propagation in LFVV without compromising real-time performance or storage compactness. Extensive experiments demonstrate that \textbf{SoLAR} achieves state-of-the-art reconstruction performance while maintaining minimum storage overhead, which provides a new direction for LFVV reconstruction and advances the practical deployment of immersive systems. Demo free-viewpoint videos are provided in the supplementary material. |
| title | SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.07346 |