Video Generation
( Various Video Generation Tasks. Gif credit: MaGViT )
Papers
Showing 41–50 of 1466 papers
All datasetsUCF-101BAIR Robot PushingSky Time-lapseUCF-101 16 frames, 64x64, UnconditionalUCF-101 16 frames, Unconditional, Single GPULAION-400MTaichiUCF-101 16 frames, 128x128, UnconditionalKinetics-600 12 frames, 64x64How2SignKinetics-600 12 frames, 128x128Kinetics-600 48 frames, 64x64
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MCVD | FVD16 | 2,460 | — | Unverified |
| 2 | VDM | FVD16 | 1,396 | — | Unverified |
| 3 | TGAN-v2 (128x128) | FVD16 | 1,209 | — | Unverified |
| 4 | MCVD (64x64) | FVD16 | 1,143 | — | Unverified |
| 5 | MoCoGAN-HD (256x256, unconditional) | FVD16 | 700 | — | Unverified |
| 6 | MagicVideo (256x256, text-conditional) | FVD16 | 699 | — | Unverified |
| 7 | TATS (256x256) | FVD16 | 635 | — | Unverified |
| 8 | FIFO-Diffusion | FVD128 | 596.64 | — | Unverified |
| 9 | DIGAN (128x128, unconditional) | FVD16 | 577 | — | Unverified |
| 10 | LVDM (256x256, unconditional) | FVD16 | 552 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MoCoGAN | FVD score | 503 | — | Unverified |
| 2 | Baseline (from LVT) | FVD score | 320.9 | — | Unverified |
| 3 | SVG-FP (from FVD) | FVD score | 315.5 | — | Unverified |
| 4 | CDNA (from FVD) | FVD score | 296.5 | — | Unverified |
| 5 | SV2P (from FVD) | FVD score | 262.5 | — | Unverified |
| 6 | SVG-LP (from vRNN) | FVD score | 256.62 | — | Unverified |
| 7 | WAM | FVD score | 159.6 | — | Unverified |
| 8 | VRNN 1L | FVD score | 149.22 | — | Unverified |
| 9 | SAVP (from vRNN) | FVD score | 143.43 | — | Unverified |
| 10 | Hier-VRNN | FVD score | 143.4 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MoCoGAN-HD (128x128) | FVD 16 | 183.6 | — | Unverified |
| 2 | TATS (128x128) | FVD 16 | 132.6 | — | Unverified |
| 3 | Long-video GAN (256x256) | FVD 16 | 116.5 | — | Unverified |
| 4 | DIGAN (128x128) | FVD 16 | 114.6 | — | Unverified |
| 5 | Long-video GAN (128x128) | FVD 16 | 107.5 | — | Unverified |
| 6 | LVDM (256x256) | FVD 16 | 95.2 | — | Unverified |
| 7 | DDMI | FVD 16 | 66.25 | — | Unverified |
| 8 | Latte + LeanVAE | FVD 16 | 49.59 | — | Unverified |
| 9 | StyleSV (256x256) | FVD 16 | 49 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Video Diffusion Model | Inception Score | 57 | — | Unverified |
| 2 | TGAN-ODE | Inception Score | 15.2 | — | Unverified |
| 3 | TGAN-F | Inception Score | 13.62 | — | Unverified |
| 4 | MoCoGAN | Inception Score | 12.42 | — | Unverified |
| 5 | MoCoGAN-MDP | Inception Score | 11.86 | — | Unverified |
| 6 | TGAN-SVC | Inception Score | 11.85 | — | Unverified |
| 7 | VGAN | Inception Score | 8.18 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TGAN-F | Inception Score | 22.91 | — | Unverified |
| 2 | TGANv2 | Inception Score | 21.45 | — | Unverified |
| 3 | TGANv2-ODE | Inception Score | 21.02 | — | Unverified |
| 4 | MoCoGAN | Inception Score | 12.42 | — | Unverified |
| 5 | MoCoGAN-MDP | Inception Score | 11.86 | — | Unverified |
| 6 | TGAN-SVC | Inception Score | 11.85 | — | Unverified |
| 7 | VGAN | Inception Score | 8.18 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Imagen original (constant=6) | CLIP R-Precision | 92.12 | — | Unverified |
| 2 | Imagen fully distilled (oscillate (15,1)) | CLIP R-Precision | 90.97 | — | Unverified |
| 3 | Imagen distilled (constant=6) | CLIP R-Precision | 90.88 | — | Unverified |
| 4 | Imagen original (oscillate(15,1)) | CLIP R-Precision | 89.91 | — | Unverified |
| 5 | Imagen fully distilled (constant=6) | CLIP R-Precision | 89.68 | — | Unverified |
| 6 | Imagen distilled (oscillate (15,1)) | CLIP R-Precision | 88.78 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DIGAN (256x256) | FVD16 | 156.7 | — | Unverified |
| 2 | MoCoGAN-HD (128x128) | FVD16 | 144.7 | — | Unverified |
| 3 | DIGAN (128x128) | FVD16 | 128.1 | — | Unverified |
| 4 | LVDM (256x256) | FVD16 | 99 | — | Unverified |
| 5 | TATS (128x128) | FVD16 | 94.6 | — | Unverified |
| 6 | StyleSV (256x256) | FVD16 | 82.6 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TGANv2 (2020) | Inception Score | 28.87 | — | Unverified |
| 2 | DVD-GAN | Inception Score | 27.38 | — | Unverified |
| 3 | VideoGPT | Inception Score | 24.69 | — | Unverified |
| 4 | TGANv2 | Inception Score | 24.34 | — | Unverified |
| 5 | TGAN-F | Inception Score | 22.91 | — | Unverified |
| 6 | TGANv2-ODE | Inception Score | 21.02 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | INR-V | FVD16 | 144 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DVD-GAN | FID | 2.16 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DVD-GAN | FID | 12.92 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DiT-XL/2 + CVAE-FT-SE | FID | 8.59 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | VideoAssembler (Zero-Shot, 256x256, class-conditional) | FVD16 | 252 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | PG-SWGAN-3D | FID | 404.1 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | StyleSV | FVD16 | 207.2 | — | Unverified |