Video Generation On Ucf 101
평가 지표
FVD16
Inception Score
KVD16
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | FVD16 | Inception Score | KVD16 |
|---|---|---|---|
| generating-videos-with-dynamics-aware-1 | 465 | 59.68 | 39.6 |
| masked-conditional-video-diffusion-for | 1143 | - | - |
| magvit-masked-generative-video-transformer | 265 | - | - |
| preserve-your-own-correlation-a-noise-prior | 355.19 | 47.76 | - |
| latent-video-diffusion-models-for-high | 552 | - | 42 |
| long-video-generation-with-time-agnostic | 332 | 79.28 | - |
| make-pixels-dance-high-dynamic-video | 242.82 | 42.10 | - |
| acdit-interpolating-autoregressive | 90 | - | - |
| lumiere-a-space-time-diffusion-model-for | 332.49 | 37.54 | - |
| tell-me-what-happened-unifying-text-guided | 328 | 73.7 | - |
| magvit-masked-generative-video-transformer | 76±2 | 89.27±0.15 | - |
| make-a-video-text-to-video-generation-without | 367.23 | 33 | - |
| omnitokenizer-a-joint-image-video-tokenizer | 191 | - | - |
| make-a-video-text-to-video-generation-without | 81.25 | 82.55 | - |
| grid-diffusion-models-for-text-to-video-1 | 340.0 | 62.88 | - |
| decomposed-diffusion-models-for-high-quality | 220 | 72.22 | - |
| latent-video-diffusion-models-for-high | 1396 | - | 116 |
| videoassembler-identity-consistent-video | 346.84 | 48.01 | - |
| video-lavit-unified-video-language-pre | 280.57 | 44.26 | - |
| language-model-beats-diffusion-tokenizer-is | 58±3 | - | - |
| larp-tokenizing-videos-with-a-learned-1 | 57 | - | - |
| lavie-high-quality-video-generation-with | 526.30 | - | - |
| towards-end-to-end-generative-modeling-of | 438 | 65.93 | - |
| preserve-your-own-correlation-a-noise-prior | 310 | 60.01 | - |
| long-video-generation-with-time-agnostic | 635 | - | 55 |
| decomposed-diffusion-models-for-high-quality | 173 | 80.03 | - |
| generating-videos-with-dynamics-aware-1 | 577 | 32.70 | - |
| align-your-latents-high-resolution-video | 550.61 | 33.45 | - |
| regis-refining-generated-videos-via-iterative | 141 | - | - |
| cogvideo-large-scale-pretraining-for-text-to | 305 | 51.11 | - |
| videopoet-a-large-language-model-for-zero | 355 | 38.44 | - |
| magicvideo-efficient-video-generation-with | 699 | - | - |
| latent-video-diffusion-models-for-high | 2460 | - | 148 |
| photorealistic-video-generation-with | 36±2 | - | - |
| vidm-video-implicit-diffusion-models | 294.7 | - | - |
| latent-video-diffusion-models-for-high | 1209 | - | - |
| latent-video-diffusion-models-for-high | 372 | - | 27 |
| a-good-image-generator-is-what-you-need-for-1 | 700 | 33.95 | - |
| long-context-autoregressive-video-modeling | 57 | - | - |
| photorealistic-video-generation-with | 258.1 | 35.1 | - |
| hierarchical-patch-diffusion-models-for-high-1 | 66.32 | 87.68 | - |
| fifo-diffusion-generating-infinite-videos | - | 74.44 | - |
| tell-me-what-happened-unifying-text-guided | 395 | 58.3 | - |
| long-video-generation-with-time-agnostic | 420 | 57.63 | - |
| language-model-beats-diffusion-tokenizer-is | 109 | - | - |
| magvit-masked-generative-video-transformer | 159±2 | 83.55±0.14 | - |