{"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/ddmi-domain-agnostic-latent-diffusion-models","title":"DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations","arxiv_id":"2401.12517","date":"2024-01-23","proceeding":null,"authors":["Dogyun Park","Sihyeon Kim","Sojin Lee","Hyunwoo J. Kim"],"abstract":"Recent studies have introduced a new class of generative models for synthesizing implicit neural representations (INRs) that capture arbitrary continuous signals in various domains. These models opened the door for domain-agnostic generative models, but they often fail to achieve high-quality generation. We observed that the existing methods generate the weights of neural networks to parameterize INRs and evaluate the network with fixed positional embeddings (PEs). Arguably, this architecture limits the expressive power of generative models and results in low-quality INR generation. To address this limitation, we propose Domain-agnostic Latent Diffusion Model for INRs (DDMI) that generates adaptive positional embeddings instead of neural networks' weights. Specifically, we develop a Discrete-to-continuous space Variational AutoEncoder (D2C-VAE), which seamlessly connects discrete data and the continuous signal functions in the shared latent space. Additionally, we introduce a novel conditioning mechanism for evaluating INRs with the hierarchically decomposed PEs to further enhance expressive power. Extensive experiments across four modalities, e.g., 2D images, 3D shapes, Neural Radiance Fields, and videos, with seven benchmark datasets, demonstrate the versatility of DDMI and its superior performance compared to the existing INR generative models.","url_abs":"https://arxiv.org/abs/2401.12517v2","url_pdf":"https://arxiv.org/pdf/2401.12517v2.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":"ddmi-domain-agnostic-latent-diffusion-models","repo_url":"https://github.com/mlvlab/DDMI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-afhq-cat","task":"Image Generation","dataset":"AFHQ Cat","model":"DDMI","rank_in_archive_order":6,"of":8,"metrics":{"FID":"4.27"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-afhq-dog","task":"Image Generation","dataset":"AFHQ Dog","model":"DDMI","rank_in_archive_order":5,"of":6,"metrics":{"FID":"8.54"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-hq-256x256","task":"Image Generation","dataset":"CelebA-HQ 256x256","model":"DDMI","rank_in_archive_order":10,"of":19,"metrics":{"FID":"8.73"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-sky-time-lapse","task":"Video Generation","dataset":"Sky Time-lapse","model":"DDMI","rank_in_archive_order":3,"of":9,"metrics":{"FVD 16":"66.25"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.12517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12517"}},"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/mlvlab/DDMI","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"ran_violates":2,"ran_draft_wrong":5,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":21,"ran":17,"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":0,"samples":[{"code_sha256_prefix":"4206702962945b57","entry":"DiffAugment","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/diffaugment.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/diffaugment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4206702962945b57"}},{"code_sha256_prefix":"984662e094837171","entry":"adopt_weight","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/perceptual.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/perceptual.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"984662e094837171"}},{"code_sha256_prefix":"9ca749a5ce7dc9a6","entry":"calculate_activation_statistics","repo":"mlvlab/DDMI","repo_kind":"official","path":"evals/fid/fid_score.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/evals/fid/fid_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ca749a5ce7dc9a6"}},{"code_sha256_prefix":"8e6b5059f61d84e6","entry":"chamfer_distance_naive","repo":"mlvlab/DDMI","repo_kind":"official","path":"convocc/src/common.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/convocc/src/common.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e6b5059f61d84e6"}},{"code_sha256_prefix":"0072de07b144b152","entry":"compute_iou","repo":"mlvlab/DDMI","repo_kind":"official","path":"convocc/src/common.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/convocc/src/common.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0072de07b144b152"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"mlvlab/DDMI","repo_kind":"official","path":"diffusion/ddpm.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/diffusion/ddpm.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"mlvlab/DDMI","repo_kind":"official","path":"diffusion/ddpm.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/diffusion/ddpm.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"69fdcf265bb8f96e","entry":"get_activations","repo":"mlvlab/DDMI","repo_kind":"official","path":"evals/fid/fid_score.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/evals/fid/fid_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69fdcf265bb8f96e"}},{"code_sha256_prefix":"22a83df891d750c6","entry":"hinge_d_loss","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/perceptual.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/perceptual.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22a83df891d750c6"}},{"code_sha256_prefix":"e39d881796e8d67e","entry":"is_url","repo":"mlvlab/DDMI","repo_kind":"official","path":"convocc/src/checkpoints.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/convocc/src/checkpoints.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e39d881796e8d67e"}},{"code_sha256_prefix":"104973640b230918","entry":"noise_like","repo":"mlvlab/DDMI","repo_kind":"official","path":"diffusion/ddpm.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/diffusion/ddpm.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"104973640b230918"}},{"code_sha256_prefix":"7257fdf155f5ef45","entry":"normalize_tensor","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/lpips.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/lpips.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7257fdf155f5ef45"}},{"code_sha256_prefix":"011230b2b9b8fb6f","entry":"rand_brightness","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/diffaugment.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/diffaugment.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"011230b2b9b8fb6f"}},{"code_sha256_prefix":"5b0d8787e670fc63","entry":"rand_saturation","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/diffaugment.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/diffaugment.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b0d8787e670fc63"}},{"code_sha256_prefix":"c369c8d351cb82f8","entry":"scale_to_half_unit_sphere","repo":"mlvlab/DDMI","repo_kind":"official","path":"evals_3d/compute_metrics_3d.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/evals_3d/compute_metrics_3d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c369c8d351cb82f8"}},{"code_sha256_prefix":"f36a62b0569c535d","entry":"scale_to_unit_sphere","repo":"mlvlab/DDMI","repo_kind":"official","path":"evals_3d/compute_metrics_3d.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/evals_3d/compute_metrics_3d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f36a62b0569c535d"}},{"code_sha256_prefix":"263c54290c553ddd","entry":"vanilla_d_loss","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/perceptual.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/perceptual.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"263c54290c553ddd"}},{"code_sha256_prefix":"0def50a351111624","entry":"calculate_frechet_distance","repo":"mlvlab/DDMI","repo_kind":"official","path":"evals/fid/fid_score.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/evals/fid/fid_score.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0def50a351111624"}},{"code_sha256_prefix":"6ce9524fa24899fa","entry":"get_ckpt_path","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/lpips.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/lpips.py","link_basis":"first_harvest_node","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":"6ce9524fa24899fa"}},{"code_sha256_prefix":"3b4e062ced70eb9f","entry":"load_config","repo":"mlvlab/DDMI","repo_kind":"official","path":"convocc/src/config.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/convocc/src/config.py","link_basis":"first_harvest_node","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":"3b4e062ced70eb9f"}},{"code_sha256_prefix":"c8d9d38b144e401f","entry":"md5_hash","repo":"mlvlab/DDMI","repo_kind":"official","path":"losses/lpips.py","file_url":"https://github.com/mlvlab/DDMI/blob/HEAD/losses/lpips.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":"c8d9d38b144e401f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}