tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918365613785088 |
|---|---|
| author | Wang, Chen Tan, Hao Yifan, Wang Chen, Zhiqin Liu, Yuheng Sunkavalli, Kalyan Bi, Sai Liu, Lingjie Hu, Yiwei |
| author_facet | Wang, Chen Tan, Hao Yifan, Wang Chen, Zhiqin Liu, Yuheng Sunkavalli, Kalyan Bi, Sai Liu, Lingjie Hu, Yiwei |
| contents | We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability. Our framework efficiently compresses multiple image observations into the fast weights of the TTT layer, forming an implicit 3D representation in the latent space that can be decoded into various explicit formats, such as Gaussian Splats (GS) for downstream applications. The online learning variant of our model supports progressive 3D reconstruction and refinement from streaming observations. We demonstrate that pretraining on novel view synthesis tasks effectively transfers to explicit 3D modeling, resulting in improved reconstruction quality and faster convergence. Extensive experiments show that our method achieves superior performance in feedforward 3D Gaussian reconstruction compared to state-of-the-art approaches on both objects and scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20160 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction Wang, Chen Tan, Hao Yifan, Wang Chen, Zhiqin Liu, Yuheng Sunkavalli, Kalyan Bi, Sai Liu, Lingjie Hu, Yiwei Computer Vision and Pattern Recognition We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability. Our framework efficiently compresses multiple image observations into the fast weights of the TTT layer, forming an implicit 3D representation in the latent space that can be decoded into various explicit formats, such as Gaussian Splats (GS) for downstream applications. The online learning variant of our model supports progressive 3D reconstruction and refinement from streaming observations. We demonstrate that pretraining on novel view synthesis tasks effectively transfers to explicit 3D modeling, resulting in improved reconstruction quality and faster convergence. Extensive experiments show that our method achieves superior performance in feedforward 3D Gaussian reconstruction compared to state-of-the-art approaches on both objects and scenes. |
| title | tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.20160 |