Collections:
- Name: VPD
  License: Apache License 2.0
  Metadata:
    Training Data:
    - NYU
  Paper:
    Title: Unleashing Text-to-Image Diffusion Models for Visual Perception
    URL: https://arxiv.org/abs/2303.02153
  README: configs/vpd/README.md
  Frameworks:
  - PyTorch
Models:
- Name: vpd_sd_4xb8-25k_nyu-480x480
  In Collection: VPD
  Results:
    Task: Depth Estimation
    Dataset: NYU
    Metrics:
      RMSE: 0.253
  Config: configs/vpd/vpd_sd_4xb8-25k_nyu-480x480.py
  Metadata:
    Training Data: NYU
    Batch Size: 32
    Architecture:
    - Stable-Diffusion
    Training Resources: 8x A100 GPUS
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vpd/vpd_sd_4xb8-25k_nyu-480x480_20230908-66144bc4.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vpd/vpd_sd_4xb8-25k_nyu-480x480_20230908.json
  Paper:
    Title: 'High-Resolution Image Synthesis with Latent Diffusion Models'
    URL: https://arxiv.org/abs/2112.10752
  Code: https://github.com/open-mmlab/mmsegmentation/tree/main/mmseg/models/backbones/vpd.py#L333
  Framework: PyTorch
- Name: vpd_sd_4xb8-25k_nyu-512x512
  In Collection: VPD
  Alias: vpd_depth
  Results:
    Task: Depth Estimation
    Dataset: NYU
    Metrics:
      RMSE: 0.258
  Config: configs/vpd/vpd_sd_4xb8-25k_nyu-512x512.py
  Metadata:
    Training Data: NYU
    Batch Size: 32
    Architecture:
    - Stable-Diffusion
    Training Resources: 8x A100 GPUS
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vpd/vpd_sd_4xb8-25k_nyu-512x512_20230918-60cefcff.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vpd/vpd_sd_4xb8-25k_nyu-512x512_20230918.json
  Paper:
    Title: 'High-Resolution Image Synthesis with Latent Diffusion Models'
    URL: https://arxiv.org/abs/2112.10752
  Code: https://github.com/open-mmlab/mmsegmentation/tree/main/mmseg/models/backbones/vpd.py#L333
  Framework: PyTorch