SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation

Yuxuan Zhang, Yiren Song, Jiaming Liu, Rui Wang, Jinpeng Yu, Hao Tang, Huaxia Li, Xu Tang, Yao Hu, Han Pan, Zhongliang Jing; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 8069-8078

Abstract


Recent advancements in subject-driven image generation have led to zero-shot generation yet precise selection and focus on crucial subject representations remain challenging. Addressing this we introduce the SSR-Encoder a novel architecture designed for selectively capturing any subject from single or multiple reference images. It responds to various query modalities including text and masks without necessitating test-time fine-tuning. The SSR-Encoder combines a Token-to-Patch Aligner that aligns query inputs with image patches and a Detail-Preserving Subject Encoder for extracting and preserving fine features of the subjects thereby generating subject embeddings. These embeddings used in conjunction with original text embeddings condition the generation process. Characterized by its model generalizability and efficiency the SSR-Encoder adapts to a range of custom models and control modules. Enhanced by the Embedding Consistency Regularization Loss for improved training our extensive experiments demonstrate its effectiveness in versatile and high-quality image generation indicating its broad applicability.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yuxuan and Song, Yiren and Liu, Jiaming and Wang, Rui and Yu, Jinpeng and Tang, Hao and Li, Huaxia and Tang, Xu and Hu, Yao and Pan, Han and Jing, Zhongliang}, title = {SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8069-8078} }