{"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/badgr-bundle-adjustment-diffusion-conditioned","title":"BADGR: Bundle Adjustment Diffusion Conditioned by GRadients for Wide-Baseline Floor Plan Reconstruction","arxiv_id":"2503.19340","date":"2025-03-25","proceeding":"CVPR 2025 1","authors":["Yuguang Li","Ivaylo Boyadzhiev","Zixuan Liu","Linda Shapiro","Alex Colburn"],"abstract":"Reconstructing precise camera poses and floor plan layouts from wide-baseline RGB panoramas is a difficult and unsolved problem. We introduce BADGR, a novel diffusion model that jointly performs reconstruction and bundle adjustment (BA) to refine poses and layouts from a coarse state, using 1D floor boundary predictions from dozens of images of varying input densities. Unlike a guided diffusion model, BADGR is conditioned on dense per-entity outputs from a single-step Levenberg Marquardt (LM) optimizer and is trained to predict camera and wall positions while minimizing reprojection errors for view-consistency. The objective of layout generation from denoising diffusion process complements BA optimization by providing additional learned layout-structural constraints on top of the co-visible features across images. These constraints help BADGR to make plausible guesses on spatial relations which help constrain pose graph, such as wall adjacency, collinearity, and learn to mitigate errors from dense boundary observations with global contexts. BADGR trains exclusively on 2D floor plans, simplifying data acquisition, enabling robust augmentation, and supporting variety of input densities. Our experiments and analysis validate our method, which significantly outperforms the state-of-the-art pose and floor plan layout reconstruction with different input densities.","url_abs":"https://arxiv.org/abs/2503.19340v1","url_pdf":"https://arxiv.org/pdf/2503.19340v1.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":[],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"layout-generation","task_name":"Layout Generation"},{"task_slug":"multi-view-3d-reconstruction","task_name":"Multi-View 3D Reconstruction"},{"task_slug":"multi-view-floor-layout-reconstruction-n-view","task_name":"Multi-view Floor Layout Reconstruction (N-view)"},{"task_slug":"panorama-pose-estimation-n-view","task_name":"Panorama Pose Estimation (N-view)"},{"task_slug":"room-layout-estimation","task_name":"Room Layout Estimation"}],"methods":[{"method_slug":"badgr","method_name":"BADGR"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[{"slug":"badgr","name":"BADGR","full_name":"Bundle Adjustment Diffusion Conditioned by Gradients"}],"results":[{"leaderboard":"/sota/panorama-pose-estimation-n-view-on-zind","task":"Panorama Pose Estimation (N-view)","dataset":"ZInd","model":"BADGR","rank_in_archive_order":1,"of":5,"metrics":{"Mean Rotation Error (0.6 pano per space)":"0.24","Mean Rotation Error (1 pano per space)":"11.2","Mean Rotation Error (2 pano per space)":"10.7","Mean Rotation Error (5 panos)":"0.25","Mean Translation Error (0.6 pano per space)":"12.2","Mean Translation Error (5 panos)":"10.4"},"uses_additional_data":false},{"leaderboard":"/sota/panorama-pose-estimation-n-view-on-zind","task":"Panorama Pose Estimation (N-view)","dataset":"ZInd","model":"Planar BA","rank_in_archive_order":2,"of":5,"metrics":{"Mean Translation Error (0.6 pano per space)":"19.1"},"uses_additional_data":false},{"leaderboard":"/sota/panorama-pose-estimation-n-view-on-zind","task":"Panorama Pose Estimation (N-view)","dataset":"ZInd","model":"CovisPose","rank_in_archive_order":3,"of":5,"metrics":{"Mean Rotation Error (0.6 pano per space)":"1.83","Mean Rotation Error (1 pano per space)":"23","Mean Rotation Error (2 pano per space)":"22.3","Mean Translation Error (0.6 pano per space)":"22.9"},"uses_additional_data":false},{"leaderboard":"/sota/panorama-pose-estimation-n-view-on-zind","task":"Panorama Pose Estimation (N-view)","dataset":"ZInd","model":"GraphCovis","rank_in_archive_order":4,"of":5,"metrics":{"Mean Rotation Error (5 panos)":"3.29","Mean Translation Error (5 panos)":"17.2"},"uses_additional_data":false},{"leaderboard":"/sota/panorama-pose-estimation-n-view-on-zind","task":"Panorama Pose Estimation (N-view)","dataset":"ZInd","model":"Guided Diffusion (Planar BA + HouseDiffusion)","rank_in_archive_order":5,"of":5,"metrics":{"Mean Translation Error (1 pano per space)":"15.0","Mean Translation Error (2 pano per space)":"13.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.19340","atlas_url":"https://app.syntology.ai/?focus=2503.19340","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":"2503.19340"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2503.19340\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2503.19340"},"call":"get_concepts_for_paper(arxiv_id=\"2503.19340\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2cc20955046ea06477682fc4fa0a89fe2c6d72311dd5423e7326b8d017fcc5bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}