SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918408977645568 |
|---|---|
| author | Qiu, Zhicheng Meng, Jiarui Luo, Tong-an Huang, Yican Feng, Xuan Li, Xuanfu Xu, ZHan |
| author_facet | Qiu, Zhicheng Meng, Jiarui Luo, Tong-an Huang, Yican Feng, Xuan Li, Xuanfu Xu, ZHan |
| contents | We propose SLARM, a feed-forward model that unifies dynamic scene reconstruction, semantic understanding, and real-time streaming inference. SLARM captures complex, non-uniform motion through higher-order motion modeling, trained solely on differentiable renderings without any flow supervision. Besides, SLARM distills semantic features from LSeg to obtain language-aligned representations. This design enables semantic querying via natural language, and the tight coupling between semantics and geometry further enhances the accuracy and robustness of dynamic reconstruction. Moreover, SLARM processes image sequences using window-based causal attention, achieving stable, low-latency streaming inference without accumulating memory cost. Within this unified framework, SLARM achieves state-of-the-art results in dynamic estimation, rendering quality, and scene parsing, improving motion accuracy by 21%, reconstruction PSNR by 1.6 dB, and segmentation mIoU by 20% over existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22893 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes Qiu, Zhicheng Meng, Jiarui Luo, Tong-an Huang, Yican Feng, Xuan Li, Xuanfu Xu, ZHan Computer Vision and Pattern Recognition We propose SLARM, a feed-forward model that unifies dynamic scene reconstruction, semantic understanding, and real-time streaming inference. SLARM captures complex, non-uniform motion through higher-order motion modeling, trained solely on differentiable renderings without any flow supervision. Besides, SLARM distills semantic features from LSeg to obtain language-aligned representations. This design enables semantic querying via natural language, and the tight coupling between semantics and geometry further enhances the accuracy and robustness of dynamic reconstruction. Moreover, SLARM processes image sequences using window-based causal attention, achieving stable, low-latency streaming inference without accumulating memory cost. Within this unified framework, SLARM achieves state-of-the-art results in dynamic estimation, rendering quality, and scene parsing, improving motion accuracy by 21%, reconstruction PSNR by 1.6 dB, and segmentation mIoU by 20% over existing methods. |
| title | SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.22893 |