Papers › BADGR: Bundle Adjustment Diffusion Conditioned by GRadients for Wide-Baseline Floor...
BADGR: Bundle Adjustment Diffusion Conditioned by GRadients for Wide-Baseline Floor Plan Reconstruction
Yuguang Li, Ivaylo Boyadzhiev, Zixuan Liu, Linda Shapiro, Alex Colburn
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Panorama Pose Estimation (N-view) | ZInd | BADGR | Mean Rotation Error (0.6 pano per space) | 0.24 | #1 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | BADGR | Mean Rotation Error (1 pano per space) | 11.2 | #1 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | BADGR | Mean Rotation Error (2 pano per space) | 10.7 | #1 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | BADGR | Mean Rotation Error (5 panos) | 0.25 | #1 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | BADGR | Mean Translation Error (0.6 pano per space) | 12.2 | #1 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | BADGR | Mean Translation Error (5 panos) | 10.4 | #1 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | Planar BA | Mean Translation Error (0.6 pano per space) | 19.1 | #2 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | CovisPose | Mean Rotation Error (0.6 pano per space) | 1.83 | #3 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | CovisPose | Mean Rotation Error (1 pano per space) | 23 | #3 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | CovisPose | Mean Rotation Error (2 pano per space) | 22.3 | #3 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | CovisPose | Mean Translation Error (0.6 pano per space) | 22.9 | #3 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | GraphCovis | Mean Rotation Error (5 panos) | 3.29 | #4 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | GraphCovis | Mean Translation Error (5 panos) | 17.2 | #4 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | Guided Diffusion (Planar BA + HouseDiffusion) | Mean Translation Error (1 pano per space) | 15.0 | #5 of 5 | Archive leaderboard | report |
| Panorama Pose Estimation (N-view) | ZInd | Guided Diffusion (Planar BA + HouseDiffusion) | Mean Translation Error (2 pano per space) | 13.4 | #5 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: BADGR
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections