L4GM: Large 4D Gaussian Reconstruction Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913391795240960 |
|---|---|
| author | Ren, Jiawei Xie, Kevin Mirzaei, Ashkan Liang, Hanxue Zeng, Xiaohui Kreis, Karsten Liu, Ziwei Torralba, Antonio Fidler, Sanja Kim, Seung Wook Ling, Huan |
| author_facet | Ren, Jiawei Xie, Kevin Mirzaei, Ashkan Liang, Hanxue Zeng, Xiaohui Kreis, Karsten Liu, Ziwei Torralba, Antonio Fidler, Sanja Kim, Seung Wook Ling, Huan |
| contents | We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Key to our success is a novel dataset of multiview videos containing curated, rendered animated objects from Objaverse. This dataset depicts 44K diverse objects with 110K animations rendered in 48 viewpoints, resulting in 12M videos with a total of 300M frames. We keep our L4GM simple for scalability and build directly on top of LGM, a pretrained 3D Large Reconstruction Model that outputs 3D Gaussian ellipsoids from multiview image input. L4GM outputs a per-frame 3D Gaussian Splatting representation from video frames sampled at a low fps and then upsamples the representation to a higher fps to achieve temporal smoothness. We add temporal self-attention layers to the base LGM to help it learn consistency across time, and utilize a per-timestep multiview rendering loss to train the model. The representation is upsampled to a higher framerate by training an interpolation model which produces intermediate 3D Gaussian representations. We showcase that L4GM that is only trained on synthetic data generalizes extremely well on in-the-wild videos, producing high quality animated 3D assets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10324 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | L4GM: Large 4D Gaussian Reconstruction Model Ren, Jiawei Xie, Kevin Mirzaei, Ashkan Liang, Hanxue Zeng, Xiaohui Kreis, Karsten Liu, Ziwei Torralba, Antonio Fidler, Sanja Kim, Seung Wook Ling, Huan Computer Vision and Pattern Recognition Machine Learning We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Key to our success is a novel dataset of multiview videos containing curated, rendered animated objects from Objaverse. This dataset depicts 44K diverse objects with 110K animations rendered in 48 viewpoints, resulting in 12M videos with a total of 300M frames. We keep our L4GM simple for scalability and build directly on top of LGM, a pretrained 3D Large Reconstruction Model that outputs 3D Gaussian ellipsoids from multiview image input. L4GM outputs a per-frame 3D Gaussian Splatting representation from video frames sampled at a low fps and then upsamples the representation to a higher fps to achieve temporal smoothness. We add temporal self-attention layers to the base LGM to help it learn consistency across time, and utilize a per-timestep multiview rendering loss to train the model. The representation is upsampled to a higher framerate by training an interpolation model which produces intermediate 3D Gaussian representations. We showcase that L4GM that is only trained on synthetic data generalizes extremely well on in-the-wild videos, producing high quality animated 3D assets. |
| title | L4GM: Large 4D Gaussian Reconstruction Model |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2406.10324 |