Video Prediction On Bair Robot Pushing 1
Métriques
FVD
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | FVD | Paper Title | Repository |
|---|---|---|---|
| MAGVIT (-B-FP) | 76±0.1 | MAGVIT: Masked Generative Video Transformer | |
| DVD-GAN-FP | 109.8 | Adversarial Video Generation on Complex Datasets | |
| Phenaki | 97 | Phenaki: Variable Length Video Generation From Open Domain Textual Description | |
| DVG | 120.03 | Diverse Video Generation using a Gaussian Process Trigger | |
| MMVG | 85.2 | Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation | |
| MAGVIT (-L-FP) | 62±0.1 | MAGVIT: Masked Generative Video Transformer |
0 of 6 row(s) selected.