Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2405.20327 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917753369133056 |
|---|---|
| author | Wang, Chen Gu, Jiatao Long, Xiaoxiao Liu, Yuan Liu, Lingjie |
| author_facet | Wang, Chen Gu, Jiatao Long, Xiaoxiao Liu, Yuan Liu, Lingjie |
| contents | Recent years have seen significant advancements in 3D generation. While methods like score distillation achieve impressive results, they often require extensive per-scene optimization, which limits their time efficiency. On the other hand, reconstruction-based approaches are more efficient but tend to compromise quality due to their limited ability to handle uncertainty. We introduce GECO, a novel method for high-quality 3D generative modeling that operates within a second. Our approach addresses the prevalent issues of uncertainty and inefficiency in existing methods through a two-stage approach. In the first stage, we train a single-step multi-view generative model with score distillation. Then, a second-stage distillation is applied to address the challenge of view inconsistency in the multi-view generation. This two-stage process ensures a balanced approach to 3D generation, optimizing both quality and efficiency. Our comprehensive experiments demonstrate that GECO achieves high-quality image-to-3D mesh generation with an unprecedented level of efficiency. We will make the code and model publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20327 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GECO: Generative Image-to-3D within a SECOnd Wang, Chen Gu, Jiatao Long, Xiaoxiao Liu, Yuan Liu, Lingjie Computer Vision and Pattern Recognition Recent years have seen significant advancements in 3D generation. While methods like score distillation achieve impressive results, they often require extensive per-scene optimization, which limits their time efficiency. On the other hand, reconstruction-based approaches are more efficient but tend to compromise quality due to their limited ability to handle uncertainty. We introduce GECO, a novel method for high-quality 3D generative modeling that operates within a second. Our approach addresses the prevalent issues of uncertainty and inefficiency in existing methods through a two-stage approach. In the first stage, we train a single-step multi-view generative model with score distillation. Then, a second-stage distillation is applied to address the challenge of view inconsistency in the multi-view generation. This two-stage process ensures a balanced approach to 3D generation, optimizing both quality and efficiency. Our comprehensive experiments demonstrate that GECO achieves high-quality image-to-3D mesh generation with an unprecedented level of efficiency. We will make the code and model publicly available. |
| title | GECO: Generative Image-to-3D within a SECOnd |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.20327 |