DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910322018746368 |
|---|---|
| author | Daniel, Tal Tamar, Aviv |
| author_facet | Daniel, Tal Tamar, Aviv |
| contents | We propose a new object-centric video prediction algorithm based on the deep latent particle (DLP) representation. In comparison to existing slot- or patch-based representations, DLPs model the scene using a set of keypoints with learned parameters for properties such as position and size, and are both efficient and interpretable. Our method, deep dynamic latent particles (DDLP), yields state-of-the-art object-centric video prediction results on several challenging datasets. The interpretable nature of DDLP allows us to perform ``what-if'' generation -- predict the consequence of changing properties of objects in the initial frames, and DLP's compact structure enables efficient diffusion-based unconditional video generation. Videos, code and pre-trained models are available: https://taldatech.github.io/ddlp-web |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_05957 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles Daniel, Tal Tamar, Aviv Computer Vision and Pattern Recognition Machine Learning We propose a new object-centric video prediction algorithm based on the deep latent particle (DLP) representation. In comparison to existing slot- or patch-based representations, DLPs model the scene using a set of keypoints with learned parameters for properties such as position and size, and are both efficient and interpretable. Our method, deep dynamic latent particles (DDLP), yields state-of-the-art object-centric video prediction results on several challenging datasets. The interpretable nature of DDLP allows us to perform ``what-if'' generation -- predict the consequence of changing properties of objects in the initial frames, and DLP's compact structure enables efficient diffusion-based unconditional video generation. Videos, code and pre-trained models are available: https://taldatech.github.io/ddlp-web |
| title | DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2306.05957 |