LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917365349875712 |
|---|---|
| author | Ding, Tianye Xie, Yiming Liang, Yiqing Chatterjee, Moitreya Miraldo, Pedro Jiang, Huaizu |
| author_facet | Ding, Tianye Xie, Yiming Liang, Yiqing Chatterjee, Moitreya Miraldo, Pedro Jiang, Huaizu |
| contents | Recent feed-forward reconstruction models like VGGT and $π^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming methods address this through learned memory mechanisms or causal attention, they require extensive retraining and may not fully leverage the strong geometric priors of state-of-the-art offline models. We propose LASER, a training-free framework that converts an offline reconstruction model into a streaming system by aligning predictions across consecutive temporal windows. We observe that simple similarity transformation ($\mathrm{Sim}(3)$) alignment fails due to layer depth misalignment: monocular scale ambiguity causes relative depth scales of different scene layers to vary inconsistently between windows. To address this, we introduce layer-wise scale alignment, which segments depth predictions into discrete layers, computes per-layer scale factors, and propagates them across both adjacent windows and timestamps. Extensive experiments show that LASER achieves state-of-the-art performance on camera pose estimation and point map reconstruction %quality with offline models while operating at 14 FPS with 6 GB peak memory on a RTX A6000 GPU, enabling practical deployment for kilometer-scale streaming videos. Project website: https://neu-vi.github.io/LASER/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13680 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction Ding, Tianye Xie, Yiming Liang, Yiqing Chatterjee, Moitreya Miraldo, Pedro Jiang, Huaizu Computer Vision and Pattern Recognition Recent feed-forward reconstruction models like VGGT and $π^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming methods address this through learned memory mechanisms or causal attention, they require extensive retraining and may not fully leverage the strong geometric priors of state-of-the-art offline models. We propose LASER, a training-free framework that converts an offline reconstruction model into a streaming system by aligning predictions across consecutive temporal windows. We observe that simple similarity transformation ($\mathrm{Sim}(3)$) alignment fails due to layer depth misalignment: monocular scale ambiguity causes relative depth scales of different scene layers to vary inconsistently between windows. To address this, we introduce layer-wise scale alignment, which segments depth predictions into discrete layers, computes per-layer scale factors, and propagates them across both adjacent windows and timestamps. Extensive experiments show that LASER achieves state-of-the-art performance on camera pose estimation and point map reconstruction %quality with offline models while operating at 14 FPS with 6 GB peak memory on a RTX A6000 GPU, enabling practical deployment for kilometer-scale streaming videos. Project website: https://neu-vi.github.io/LASER/ |
| title | LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.13680 |