RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction

Tingjun Huang; Dmitry Rudshin; Mathieu Meyer; Pietro Bonazzi; Marc Pollefeys; Emilia Szymańska

cs.CVSep 11, 2026

RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction

Authors: Tingjun Huang, Dmitry Rudshin, Mathieu Meyer, Pietro Bonazzi, Marc Pollefeys, Emilia Szymańska

Organizations: ETH Zürich · Hilti AG

Abstract

Recent developments in feed-forward 3D reconstruction resulted in models which can recover dense scene representations and camera motion solely from an image stream. However, such predictions are prone to becoming inconsistent over long trajectories, specifically in demanding environments with repetitive structures, weak textures and dynamic objects or people. One way to mitigate those challenges is to use an omnidirectional camera, which provides wide spatial coverage and captures richer visual information. Yet, the majority of models do not offer support for 360-degree imagery or require additional fine-tuning. To bridge these two aspects, we present RIGOR: a large-scale reconstruction pipeline for gravity-aligned omnidirectional videos that retains a frozen feed-forward perspective backbone and exploits each panorama as a four-view virtual rig. The rig structure is used to detect and repair locally inconsistent predictions, to retrieve loop closures through cyclic four-view consensus, and to geometrically verify candidate revisits before global optimization. Verified constraints drive a Sim(3) pose graph that corrects accumulated rotation, translation, and scale drift along the sequence. We demonstrate that the proposed consistency mechanisms improve both trajectory accuracy and reconstructed geometry over a feed-forward baseline on challenging construction-site sequences. The code is made available under this link: https://github.com/TangentH/RIGOR.

Figures & tables

Figure 1 : Conceptual illustration of the RIGOR principle, providing consistency constraints for local and global reconstruction.

Feed-forward reconstruction
Method	Pano.	Dense	Long seq.	Loop	Pano train.
DUSt3R, MASt3R,	✗	✓	✗	✗	✗
VGGT, DA3, $\pi^{3}$ , MapAnything	✗	✓	✗	✗	✗
MUSt3R	✗	✓	✓	✗	✗
Persistent reconstruction / learned SLAM
Spann3R, CUT3R, SLAM3R,	✗	✓	✓	✗	✗

Table 1 : Comparison of representative reconstruction systems, categorized by the support of panoramic images ( Pano. ), dense reconstruction ( Dense ), long sequences ( Long seq. ), explicit revisit detection with corrective optimization ( Loop ), and whether panorama-specific learned training was required ( Pano train. ). “–” denotes that the criterion is not applicable.

Figure 2 : RIGOR retains a frozen perspective predictor and uses the known four-view panorama rig for validated local repair and cyclic multi-view loop retrieval. Joint feed-forward prediction verifies the retrieved candidates before accepted loop measurements enter a global $\mathrm{Sim}(3)$ pose graph for reconstruction fusion.

Figure 3 : Per-sequence distributions of trajectory and geometry metrics.

Method	ATE RMSE [m] $\downarrow$	RPE-10s RMSE [m] $\downarrow$
DA3-Sequential	2.841	1.827
DA3-Legacy	2.704	1.797
PanoVGGT	5.206	3.991
Ours w/o Rig Repair	2.841	1.827
Ours	2.312	1.712

Table 2 : Quantitative results. We report medians over 30 trajectories and 29 runs with LiDAR geometry. Every cloud is independently registered under the same scale-adjusting evaluation protocol. Best values within each block are bold.

Figure 4 : Qualitative comparison on two challenging sequences. For each sequence, the upper row shows the estimated trajectory and the lower row shows the reconstructed point cloud. Methods that did not consistently produce complete long-sequence reconstructions are included for qualitative analysis but omitted from the main quantitative table.

Retrieval	Pair AP $\uparrow$	R@P99 $\uparrow$	W/T/L
Single-view max	0.530	0.178	–
Cyclic four-view	0.609	0.190	24/0/4
Rig repair	ROI CD $\downarrow$	ROI F@25 $\mathrm{cm}$ $\uparrow$	W/T/L
Off	0.230	0.718	–
On	0.132	0.873	28/0/1
Graph update	ATE RMSE $\downarrow$	RPE-10s RMSE $\downarrow$	W/T/L

Table 3 : Controlled component experiments. Retrieval uses 28 runs with GT-labeled revisits, geometry uses 29 LiDAR runs, and trajectory uses all 30 runs. We additionally report sequence-wise win/tie/loss (W/T/L) counts for the first metric in each ablation block. A win indicates that the full method outperforms the compared variant on that sequence according to the metric direction, a loss indicates the opposite, and values differing by less than

10^{-12}

are counted as ties. The rig-repair block is an end-to-end ablation: loop verification and graph construction are recomputed after repair is disabled.

Figure 5 : Parameter choices. (a) The fraction of 400 cyclically adjacent-view pairs per FoV returning a non-empty homography consensus increases with wider crops. At

90^{\circ}

, the crops have no designed area overlap; non-empty responses can arise from boundary sampling or ambiguous matches. (b) Raw DA3 pose consistency on the same 100 panoramas peaks at

95^{\circ}

under the common

0.1

m center and

5^{\circ}

rotation diagnostic. These rates describe the parameter comparison, not accepted repairs. (c) On one 229-panorama run under the earlier sequential/no-loop protocol, yaw-four-aligned layouts avoid incomplete capture groups, and 32/16 gives the lowest ATE in this check.

Explore similar work

Glob3R: Global Structure-from-Motion with 3D Foundation Models
Jul 10, 2026Junyuan Deng, Heng Li, Kejie Qiu +7Bundle Adjustment Multi-View 3D Reconstruction
The Hong Kong University of Science and Technology · Tongyi Lab, Alibaba Group · Nanjing University +1
GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction
Sep 17, 2026Enpeng Li, Yunzhou Zhang, Zhiyao Zhang +43D Reconstruction Monocular 3D Reconstruction
College of Information Science and Engineering, Northeastern University, China
MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos
Jul 16, 2026Ziren Gong, Xiaohan Li, Fabio Tosi +43D Reconstruction Monocular 3D Reconstruction
University of Bologna, Italy · Faculty of Dentistry, The University of Hong Kong, China · School of Instrument Science and Engineering, Southeast University, China +1

Jul 10, 2026, cs.CVJ/K move · Enter open · S save

Glob3R: Global Structure-from-Motion with 3D Foundation Models

Junyuan Deng, Heng Li, Kejie Qiu, Lingteng Qiu+6

The Hong Kong University of Science and Technology · Tongyi Lab, Alibaba Group · Nanjing University+1

Bundle Adjustment Multi-View 3D Reconstruction Structure from Motion

Open paper AskPDF arXiv

Recent 3D geometric foundation models, such as VGGT, provide robust feed-forward 3D reconstruction by directly predicting camera poses and 3D scene points from input images. However, their results remain inaccurate, and scaling them to long sequences or large unordered image sets typically requires chunk-wise processing, which can introduce drift and inconsistency. We present Glob3R, a global SfM-style reconstruction built on 3D foundation models. Our key idea is to explicitly optimize feed-forward geometric predictions. To this end, we augment a frozen Pi3X backbone with a lightweight dense matching head that predicts image warps between selected reference frames and neighboring views. These dense warps are converted into sparse but reliable multi-view feature tracks, which provide correspondence constraints for global optimization. We further introduce a keyframe-based sliding-window association strategy that propagates tracks and relative poses across overlapping windows, enabling scalable reconstruction. Finally, we perform global motion averaging and bundle adjustment to refine camera poses, reduce scale inconsistencies, and recover dense scene geometry. Extensive experiments on indoor, outdoor, large-scale driving, and unordered SfM benchmarks demonstrate that Glob3R achieves robust and accurate reconstruction. It consistently improves over feed-forward foundation-model baselines and recent scalable reconstruction methods, while being more robust than classical SfM pipelines. The refined poses also lead to higher-quality neural rendering, validating the benefit of combining foundation-model priors with global geometric optimization. Project page: https://junyuandeng.github.io/Glob3r

Abstract

Explore similar work

Glob3R: Global Structure-from-Motion with 3D Foundation Models

GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction

MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos