MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914623662325760 |
|---|---|
| author | Kwon, Minkyung Choi, Jinhyeok Shin, Youngjin Kim, Jaeyeong Lee, JongMin Kim, Seungryong |
| author_facet | Kwon, Minkyung Choi, Jinhyeok Shin, Youngjin Kim, Jaeyeong Lee, JongMin Kim, Seungryong |
| contents | We present MORPHOS, a novel autoregressive framework that generates dynamic 3D assets from videos across diverse representations, including meshes, 3D Gaussians, and radiance fields. Existing methods are typically limited to a single representation, struggle to model topological changes, or fail to maintain temporal consistency over long videos. To address these limitations, we introduce the Temporal Structured Latents (T-SLAT), a unified 4D representation that jointly encodes geometry and appearance along the temporal dimension. Leveraging T-SLAT, MORPHOS autoregressively generates dynamic 3D assets via causal attention, conditioning each frame on its preceding history to ensure temporal consistency while handling evolving topologies. We also propose a temporal-structural augmentation to mitigate error accumulation in autoregressive generation. MORPHOS achieves state-of-the-art performance in appearance and competitive results in geometry across multiple benchmarks, demonstrating superior generalization across various representations and robustness in long-horizon generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_02491 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents Kwon, Minkyung Choi, Jinhyeok Shin, Youngjin Kim, Jaeyeong Lee, JongMin Kim, Seungryong Computer Vision and Pattern Recognition We present MORPHOS, a novel autoregressive framework that generates dynamic 3D assets from videos across diverse representations, including meshes, 3D Gaussians, and radiance fields. Existing methods are typically limited to a single representation, struggle to model topological changes, or fail to maintain temporal consistency over long videos. To address these limitations, we introduce the Temporal Structured Latents (T-SLAT), a unified 4D representation that jointly encodes geometry and appearance along the temporal dimension. Leveraging T-SLAT, MORPHOS autoregressively generates dynamic 3D assets via causal attention, conditioning each frame on its preceding history to ensure temporal consistency while handling evolving topologies. We also propose a temporal-structural augmentation to mitigate error accumulation in autoregressive generation. MORPHOS achieves state-of-the-art performance in appearance and competitive results in geometry across multiple benchmarks, demonstrating superior generalization across various representations and robustness in long-horizon generation. |
| title | MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.02491 |