{"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/object-centric-slot-diffusion-1","title":"Object-Centric Slot Diffusion","arxiv_id":"2303.10834","date":"2023-03-20","proceeding":"NeurIPS 2023 11","authors":["Jindong Jiang","Fei Deng","Gautam Singh","Sungjin Ahn"],"abstract":"The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes. However, despite the high expressiveness of diffusion models in image generation, their integration into object-centric learning remains largely unexplored in this domain. In this paper, we explore the feasibility and potential of integrating diffusion models into object-centric learning and investigate the pros and cons of this approach. We introduce Latent Slot Diffusion (LSD), a novel model that serves dual purposes: it is the first object-centric learning model to replace conventional slot decoders with a latent diffusion model conditioned on object slots, and it is also the first unsupervised compositional conditional diffusion model that operates without the need for supervised annotations like text. Through experiments on various object-centric tasks, including the first application of the FFHQ dataset in this field, we demonstrate that LSD significantly outperforms state-of-the-art transformer-based decoders, particularly in more complex scenes, and exhibits superior unsupervised compositional generation quality. In addition, we conduct a preliminary investigation into the integration of pre-trained diffusion models in LSD and demonstrate its effectiveness in real-world image segmentation and generation. Project page is available at https://latentslotdiffusion.github.io","url_abs":"https://arxiv.org/abs/2303.10834v5","url_pdf":"https://arxiv.org/pdf/2303.10834v5.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":"object-centric-slot-diffusion-1","repo_url":"https://github.com/jindongjiang/latent-slot-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"object-centric-slot-diffusion-1","repo_url":"https://github.com/whieya/learning-to-compose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.10834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10834"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jindongjiang/latent-slot-diffusion","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/whieya/learning-to-compose","reach":null}],"summary":{"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":1,"repositories":1},"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"4bdd36eab04c3f62","entry":"get_1d_sincos_pos_embed_from_grid","repo":"jindongjiang/latent-slot-diffusion","repo_kind":"official","path":"src/models/utils.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"code_sha256_prefix":"f47cccc4f551b3d8","entry":"Comp_Model","repo":"whieya/learning-to-compose","repo_kind":"listed","path":"models/slot_attention/model.py","file_url":"https://github.com/whieya/learning-to-compose/blob/HEAD/models/slot_attention/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f47cccc4f551b3d8"}},{"code_sha256_prefix":"8a3405f854ecf3a4","entry":"cosine_distance","repo":"jindongjiang/latent-slot-diffusion","repo_kind":"official","path":"src/eval/eval_utils.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/eval/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a3405f854ecf3a4"}},{"code_sha256_prefix":"8f46183e80c268ef","entry":"cosine_similarity","repo":"jindongjiang/latent-slot-diffusion","repo_kind":"official","path":"src/eval/eval_utils.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/eval/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f46183e80c268ef"}},{"code_sha256_prefix":"3984e7faeca4f621","entry":"get_2d_sincos_pos_embed","repo":"jindongjiang/latent-slot-diffusion","repo_kind":"official","path":"src/models/utils.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3984e7faeca4f621"}},{"code_sha256_prefix":"4fd80de79832745d","entry":"get_2d_sincos_pos_embed_from_grid","repo":"jindongjiang/latent-slot-diffusion","repo_kind":"official","path":"src/models/utils.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4fd80de79832745d"}},{"code_sha256_prefix":"f3a05df11a6aa00c","entry":"get_mask_cosine_distance","repo":"jindongjiang/latent-slot-diffusion","repo_kind":"official","path":"src/eval/eval_utils.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/eval/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3a05df11a6aa00c"}},{"code_sha256_prefix":"c348f6b1a3946d1b","entry":"is_square","repo":"jindongjiang/latent-slot-diffusion","repo_kind":"official","path":"src/models/slot_attn.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/models/slot_attn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c348f6b1a3946d1b"}},{"code_sha256_prefix":"2370c9298b3778de","entry":"parse_args","repo":"jindongjiang/latent-slot-diffusion","repo_kind":"official","path":"src/parser.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/parser.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2370c9298b3778de"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}