deeptimhe commited on
Commit
c75454d
·
verified ·
1 Parent(s): deb5e52

add hf links

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -25,7 +25,7 @@ We train VidTok on a large-scale video dataset and evaluation reveal that VidTok
25
  Resources and technical documentation:
26
 
27
  + [GitHub](https://github.com/microsoft/VidTok)
28
- + [arXiv](https://arxiv.org/abs)
29
 
30
 
31
  ## Model Performance
@@ -34,18 +34,18 @@ The following table shows model performance evaluated on 30 test videos in [MCL_
34
 
35
  | Model | Regularizer | Causal | VCR | PSNR | SSIM | LPIPS | FVD |
36
  |------|------|------|------|------|------|------|------|
37
- | [kl_causal_488_4chn.ckpt]() | KL - 4chn | ✔️ | 4x8x8 | 29.64 | 0.852| 0.114| 194.2|
38
- | [kl_causal_488_8chn.ckpt]() | KL - 8chn | ✔️ |4x8x8 | 31.83 | 0.897| 0.083| 109.3|
39
- | [kl_causal_488_16chn.ckpt]() | KL - 16chn | ✔️ | 4x8x8 | 35.04 |0.942 |0.047 | 78.9|
40
- | [kl_causal_41616_4chn.ckpt]() | KL - 4chn | ✔️ | 4x16x16 | 25.05 | 0.711| 0.228| 549.1| |
41
- | [kl_noncausal_488_4chn.ckpt]() | KL - 4chn | ✖️ | 4x8x8 | 30.60 | 0.876 | 0.098| 157.9|
42
- | [kl_noncausal_41616_4chn.ckpt]() | KL - 4chn | ✖️ | 4x16x16 | 26.06 | 0.751 | 0.190|423.2 |
43
- | [fsq_causal_488_262144.ckpt]() | FSQ - 262,144 | ✔️ | 4x8x8 | 29.82 | 0.867 |0.106 | 160.1|
44
- | [fsq_causal_488_32768.ckpt]() | FSQ - 32,768 | ✔️ | 4x8x8 | 29.16 | 0.854 | 0.117| 196.9|
45
- | [fsq_causal_488_4096.ckpt]() | FSQ - 4096 | ✔️ | 4x8x8 | 28.36 | 0.832 | 0.133| 218.1|
46
- | [fsq_causal_41616_262144.ckpt]() | FSQ - 262,144 | ✔️ | 4x16x16 | 25.38 | 0.738 |0.206 | 430.1|
47
- | [fsq_noncausal_488_262144.ckpt]() | FSQ - 262,144 | ✖️ | 4x8x8 | 30.78 | 0.889| 0.091| 132.1|
48
- | [fsq_noncausal_41616_262144.ckpt]() | FSQ - 262,144 | ✖️ | 4x16x16 | 26.37 | 0.772| 0.171| 357.0|
49
 
50
  ## Training
51
  ### Training Data
 
25
  Resources and technical documentation:
26
 
27
  + [GitHub](https://github.com/microsoft/VidTok)
28
+ + [arXiv](https://arxiv.org/abs/)
29
 
30
 
31
  ## Model Performance
 
34
 
35
  | Model | Regularizer | Causal | VCR | PSNR | SSIM | LPIPS | FVD |
36
  |------|------|------|------|------|------|------|------|
37
+ | [vidtok_kl_causal_488_4chn](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_kl_causal_488_4chn.ckpt) | KL-4chn | ✔️ | 4x8x8 | 29.64 | 0.852| 0.114| 194.2|
38
+ | [vidtok_kl_causal_488_8chn](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_kl_causal_488_8chn.ckpt) | KL-8chn | ✔️ |4x8x8 | 31.83 | 0.897| 0.083| 109.3|
39
+ | [vidtok_kl_causal_488_16chn](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_kl_causal_488_16chn.ckpt) | KL-16chn | ✔️ | 4x8x8 | 35.04 |0.942 |0.047 | 78.9|
40
+ | [vidtok_kl_causal_41616_4chn](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_kl_causal_41616_4chn.ckpt) | KL-4chn | ✔️ | 4x16x16 | 25.05 | 0.711| 0.228| 549.1| |
41
+ | [vidtok_kl_noncausal_488_4chn](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_kl_noncausal_488_4chn.ckpt) | KL-4chn | ✖️ | 4x8x8 | 30.60 | 0.876 | 0.098| 157.9|
42
+ | [vidtok_kl_noncausal_41616_4chn](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_kl_noncausal_41616_4chn.ckpt) | KL-4chn | ✖️ | 4x16x16 | 26.06 | 0.751 | 0.190|423.2 |
43
+ | [vidtok_fsq_causal_488_262144](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_fsq_causal_488_262144.ckpt) | FSQ-262,144 | ✔️ | 4x8x8 | 29.82 | 0.867 |0.106 | 160.1|
44
+ | [vidtok_fsq_causal_488_32768](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_fsq_causal_488_32768.ckpt) | FSQ-32,768 | ✔️ | 4x8x8 | 29.16 | 0.854 | 0.117| 196.9|
45
+ | [vidtok_fsq_causal_488_4096](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_fsq_causal_488_4096.ckpt) | FSQ-4096 | ✔️ | 4x8x8 | 28.36 | 0.832 | 0.133| 218.1|
46
+ | [vidtok_fsq_causal_41616_262144](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_fsq_causal_41616_262144.ckpt) | FSQ-262,144 | ✔️ | 4x16x16 | 25.38 | 0.738 |0.206 | 430.1|
47
+ | [vidtok_fsq_noncausal_488_262144](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_fsq_noncausal_488_262144.ckpt) | FSQ-262,144 | ✖️ | 4x8x8 | 30.78 | 0.889| 0.091| 132.1|
48
+ | [vidtok_fsq_noncausal_41616_262144](https://huggingface.co/microsoft/VidTok/blob/main/checkpoints/vidtok_fsq_noncausal_41616_262144.ckpt) | FSQ-262,144 | ✖️ | 4x16x16 | 26.37 | 0.772| 0.171| 357.0|
49
 
50
  ## Training
51
  ### Training Data