{"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/neurally-guided-procedural-models-amortized","title":"Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks","arxiv_id":"1603.06143","date":"2016-03-19","proceeding":"NeurIPS 2016 12","authors":["Daniel Ritchie","Anna Thomas","Pat Hanrahan","Noah D. Goodman"],"abstract":"Probabilistic inference algorithms such as Sequential Monte Carlo (SMC)\nprovide powerful tools for constraining procedural models in computer graphics,\nbut they require many samples to produce desirable results. In this paper, we\nshow how to create procedural models which learn how to satisfy constraints. We\naugment procedural models with neural networks which control how the model\nmakes random choices based on the output it has generated thus far. We call\nsuch models neurally-guided procedural models. As a pre-computation, we train\nthese models to maximize the likelihood of example outputs generated via SMC.\nThey are then used as efficient SMC importance samplers, generating\nhigh-quality results with very few samples. We evaluate our method on\nL-system-like models with image-based constraints. Given a desired quality\nthreshold, neurally-guided models can generate satisfactory results up to 10x\nfaster than unguided models.","url_abs":"http://arxiv.org/abs/1603.06143v2","url_pdf":"http://arxiv.org/pdf/1603.06143v2.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":"neurally-guided-procedural-models-amortized","repo_url":"https://github.com/dritchie/adnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}