Dual-Layer Image Codec with Text Guidance for Hybrid Visual Perception

Official checkpoints for the paper Dual-Layer Image Codec with Text Guidance for Hybrid Visual Perception (Tianma Shen, Joseph Quan, Ying Liu).

Code: SCU-VIP-Lab/dual-layer-image-codec-with-text-guidance.

Layout

checkpoints/
  base_obj/    # base layer (object detection); same as MMCRC base_obj
    save1.ckpt โ€ฆ save4.ckpt
  human/       # enhancement layer (text-guided human reconstruction)
    save1.ckpt โ€ฆ save4.ckpt

Download

pip install -U "huggingface_hub[cli]"
hf download SCU-VIP-Lab/Dual-Layer-Image-Codec-with-Text-Guidance \
  --include "checkpoints/**" \
  --local-dir .
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support