Unsupervised Keypoints from Pretrained Diffusion Models

Eric Hedlin, Gopal Sharma, Shweta Mahajan, Xingzhe He, Hossam Isack, Abhishek Kar, Helge Rhodin, Andrea Tagliasacchi, Kwang Moo Yi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 22820-22830

Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures but performance is yet to match the supervised counterpart making their practicability questionable. We leverage the emergent knowledge within text-to-image diffusion models towards more robust unsupervised keypoints. Our core idea is to find text embeddings that would cause the generative model to consistently attend to compact regions in images (i.e. keypoints). To do so we simply optimize the text embedding such that the cross-attention maps within the denoising network are localized as Gaussians with small standard deviations. We validate our performance on multiple datasets: the CelebA CUB-200-2011 Tai-Chi-HD DeepFashion and Human3.6m datasets. We achieve significantly improved accuracy sometimes even outperforming supervised ones particularly for data that is non-aligned and less curated. Our code is publicly available at https://stablekeypoints.github.io/.