{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/the-informed-sampler-a-discriminative","title":"The Informed Sampler: A Discriminative Approach to Bayesian Inference in Generative Computer Vision Models","arxiv_id":"1402.0859","date":"2014-02-04","proceeding":null,"authors":["Varun Jampani","Sebastian Nowozin","Matthew Loper","Peter V. Gehler"],"abstract":"Computer vision is hard because of a large variability in lighting, shape,\nand texture; in addition the image signal is non-additive due to occlusion.\nGenerative models promised to account for this variability by accurately\nmodelling the image formation process as a function of latent variables with\nprior beliefs. Bayesian posterior inference could then, in principle, explain\nthe observation. While intuitively appealing, generative models for computer\nvision have largely failed to deliver on that promise due to the difficulty of\nposterior inference. As a result the community has favoured efficient\ndiscriminative approaches. We still believe in the usefulness of generative\nmodels in computer vision, but argue that we need to leverage existing\ndiscriminative or even heuristic computer vision methods. We implement this\nidea in a principled way with an \"informed sampler\" and in careful experiments\ndemonstrate it on challenging generative models which contain renderer programs\nas their components. We concentrate on the problem of inverting an existing\ngraphics rendering engine, an approach that can be understood as \"Inverse\nGraphics\". The informed sampler, using simple discriminative proposals based on\nexisting computer vision technology, achieves significant improvements of\ninference.","url_abs":"http://arxiv.org/abs/1402.0859v3","url_pdf":"http://arxiv.org/pdf/1402.0859v3.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":"the-informed-sampler-a-discriminative","repo_url":"https://github.com/mrquincle/noparama","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1402.0859","atlas_url":"https://app.syntology.ai/?focus=1402.0859","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1402.0859"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1402.0859\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1402.0859"},"call":"get_concepts_for_paper(arxiv_id=\"1402.0859\")"}],"by_repo":[{"repo":"mrquincle/noparama","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1310ecaa42a7acbcb7ca7dd0a3248511f0f63d8b3d601355be8b2de3a18366a3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}