{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/implicit-inversion-turns-clip-into-a-decoder","title":"Implicit Inversion turns CLIP into a Decoder","arxiv_id":"2505.23161","date":"2025-05-29","proceeding":null,"authors":["Antonio D'Orazio","Maria Rosaria Briglia","Donato Crisostomi","Dario Loi","Emanuele Rodolà","Iacopo Masi"],"abstract":"CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines, where a decoder is trained to map from the shared space back to images. In this work, we show that image synthesis is nevertheless possible using CLIP alone -- without any decoder, training, or fine-tuning. Our approach optimizes a frequency-aware implicit neural representation that encourages coarse-to-fine generation by stratifying frequencies across network layers. To stabilize this inverse mapping, we introduce adversarially robust initialization, a lightweight Orthogonal Procrustes projection to align local text and image embeddings, and a blending loss that anchors outputs to natural image statistics. Without altering CLIP's weights, this framework unlocks capabilities such as text-to-image generation, style transfer, and image reconstruction. These findings suggest that discriminative models may hold untapped generative potential, hidden in plain sight.","url_abs":"https://arxiv.org/abs/2505.23161v1","url_pdf":"https://arxiv.org/pdf/2505.23161v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"implicit-inversion-turns-clip-into-a-decoder","repo_url":"https://github.com/omnai-lab/implicit-inversion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"procrustes","method_name":"Procrustes"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.23161","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}