Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official Implementation of paper "A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence"
| Date | Stars |
|---|---|
| 2026-07-31 | 357 |
| 2026-08-04 | 357 |
| 2026-08-06 | 357 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence **A Tale of Two Features** explores the complementary nature of Stable Diffusion (SD) and DINOv2 features for zero-shot semantic correspondence. The results demonstrate that a simple fusion of the two features leads to state-of-the-art performance on the SPair-71k, PF-Pascal, and TSS datasets. This repository is the official implementation of the paper: [**A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence**](https://arxiv.org/abs/2305.15347) [*Junyi Zhang*](https://junyi42.github.io/), [*Charles Herrmann*](https://scholar.google.com/citations?user=LQvi5XAAAAAJ), [*Junhwa Hur*](https://hurjunhwa.github.io/), [*Luisa F. Polanía*](https://scholar.google.com/citations?user=HGLobX4AAAAJ), [*Varun Jampani*](https://varunjampani.github.io/), [*Deqing Sun*](https://deqings.github.io/), [*Ming-Hsuan Yang*](https://faculty.ucmerced.edu/mhyang/) NeurIPS, 2023. **[New!] We have released the code for [Telling Left from Right](https://github.com/Junyi42/geoaware-sc), a follow-up with better semantic correspondence.**  ## Visual Results ### Dense Correspondence <img src="assets/dense_correspondence.png" width="100%"> ### Object Swapping <div align="center"> <img src="assets/swap_aero.gif" width="32%"> <img src="assets/swap_bird.gif" width="32%"> <img src="assets/swap_bus.gif" width="32%"> </div> <div align="center"> <img src="assets/swap_car.gif" width="32%"> <img src="assets/swap_cow.gif" width="32%"> <img src="assets/swap_dog.gif" width="32%"> </div> <div align="center"> <img src="assets/swap_person.gif" width="32%"> <img src="assets/swap_sheep.gif" width="32%"> <img src="assets/swap_train.gif" width="32%"> </div> ### Object Swapping (with refinement process) <div align="center"> <img src="assets/instance_swapping_cat.png" width="49%"> <img src="assets/instance_swapping_bird.png" width="49%"> </div> ## Links * [Project Page](https://sd-complements-dino.github.io) (with additional visual results) * [arXiv Page](https://arxiv.org/abs/2305.15347) ## Environment Setup To install the required dependencies, use the following commands: ```bash conda create -n sd-dino python=3.9 conda activate sd-dino conda install pytorch=1.13.1 torchvision=0.14.1 pytorch-cuda=11.6 -c pytorch -c nvidia conda install -c "nvidia/label/cuda-11.6.1" libcusolver-dev git clone [email protected]:Junyi42/sd-dino.git cd sd-dino pip install -e . ``` (Optional) You may also want to install [xformers](https://github.com/facebookresearch/xformers) for efficient transformer implementation: ``` pip install xformers==0.0.16 ``` ## Get Started ### Prepare the data We provide the scripts to download the datasets in the `data` folder. To download specific datasets, use the following commands: * SPair-71k: ```bash bash data/prepare_spair.sh ``` * PF-Pascal: ```bash bash data/prepare_pfpascal.sh ``` * TSS: ```bash bash data/prepare_tss.sh ``` ### Evaluate the PCK Results of SPair-71k Run [pck_spair_pascal.py](pck_spair_pascal.py) file: ```bash python pck_spair_pascal.py --SAMPLE 20 ``` Note that the `SAMPLE` is the number of sampled pairs for each category, which is set to 20 by default. Set to `0` to use all the samples (settings in the paper). Additional important parameters in [pck_spair_pascal.py](pck_spair_pascal.py) include: * `--NOT_FUSE`: if set to True, only use the SD feature. * `--ONLY_DINO`: if set to True, only use the DINO feature. * `--DRAW_DENSE`: if set to True, draw the dense correspondence map. * `--DRAW_SWAP`: if set to True, draw the object swapping result. * `--DRAW_GIF`: if set to True, draw the object swapping result as a gif. * `--TOTAL_SAVE_RESULT`: number of samples to save the qualitative results, set to 0 to disable and accelerate the evaluation process. Please refer to the [pck_spair_pascal.py](pck_spair_pascal.py) file for more details. You may find samples
Excerpt of 5,806 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a5b2ffa0fb0bd66a, desc:stable diffusion