Bracketing Shows the Way: Adaptive Multi-Exposure Policy as Input for Robust Visual SLAM

Olivier Gamache; Anthony Lavertu; David-Alexandre Duclos; Jean-Michel Fortin; François Pomerleau; Philippe Giguère

cs.ROOct 23, 2026

Bracketing Shows the Way: Adaptive Multi-Exposure Policy as Input for Robust Visual SLAM

Authors: Olivier Gamache, Anthony Lavertu, David-Alexandre Duclos, Jean-Michel Fortin, François Pomerleau, Philippe Giguère

Organizations: Northern Robotics Laboratory, Université Laval, Québec City, Québec, Canada

Abstract

Rapid illumination transitions can disturb Visual SLAM (VSLAM) by saturating images before the Automatic Exposure (AE) policy adapts, removing the visual correspondences needed to maintain tracking. Our proposed methods mitigate this disturbance at two levels: B-Adapt acquires adaptive exposure brackets to cover the scene dynamic range while promoting photometric overlap, and BVSLAM directly uses the multi-exposure sequence as constraints in a factor graph state estimator without relying on High Dynamic Range (HDR) merging. We evaluate both methods against state-of-the-art approaches in nominal environments and during a repeated tunnel-exit transition at an emulated vehicle speed of 32 m s-1. In the tunnel, combining our B-Adapt with BVSLAM reduces the state estimation error by 78 % compared with AE images. These results suggest that bracketing efficiently improves visual pose estimation robustness to rapid illumination disturbances while retaining low error under nominal conditions. Our code is available at https://github.com/norlab-ulaval/bracketing-shows-the-way.

Figures & tables

Fig. 1 : Effect of a rapid low-to-high illumination transition on the visual information available for pose estimation. Left : The vehicle exits a dim tunnel ( $30\text{\,}\mathrm{lx}$ ) toward a bright outdoor scene ( $80\text{\,}000\text{\,}\mathrm{lx}$ ). Right : Camera images acquired by the vehicle during the tunnel-exit traversal shown on the left. The vertically cropped images show three successive instants ( $t_{0}$ – $t_{2}$ ) during the illumination transition. Colored points indicate the detected visual features. The AE policy adapts too slowly, saturating images, whereas B-Adapt preserves observable content across complementary exposures.

Fig. 2 : Overview of our proposed B-Adapt and BVSLAM pipeline for $n=3$ , $I_{\max}=255$ , and $W=5$ . Left : B-Adapt independently regulates the Low and High bounding brackets using one-sided intensity-tail objectives, parameterized by $\alpha$ and $\beta$ , while the intermediate Mid exposure is derived from the two bounds. Right : BVSLAM exploits the resulting bracketing sequence by associating features of images within one exposure step and a lookback window of $W$ frames from the current one (grey window). Pose colors indicate the corresponding exposure levels, while the unfilled circles denote landmarks shared across poses through the retained cross-exposure correspondences.

Fig. 3 : Left : Our experimental platform. The acquisition head combines a synchronized stereo pair with sensors used to compute reference trajectories and characterize scene illumination. Right : Examples of frames taken across our nominal (grey) and disturbance (purple) trajectories, with the evaluated approaches. B-Adapt and B-Fixed images are stacked and cropped horizontally to showcase the three image exposures.

Parameter	Symbol	Value
Number of brackets	$n$	$3$
Window size	$W$	$5$
Tail fraction	$\alpha$	$1.0\text{\,}\mathrm{\%}$
Intensity margin	$\beta$	$5$
Smoothing coefficient	$\lambda$	$0.8$
Minimum separation	$\Delta_{\min}$	$1~\text{stop}$

TABLE I: B-Adapt parameters used in our experiments.

Fig. 4 : RPE RMSE over $5\text{\,}\mathrm{m}$ windows in the nominal environments ( top ) and during the tunnel-exit disturbance ( bottom ), evaluated across state estimators ( rows ) and acquisition policies ( columns ). Disturbance results are pooled across five repeated trajectories. The outlined cell identifies our proposed combination of B-Adapt and BVSLAM .

Fig. 5 : Comparison of AE and B-Adapt around the tunnel exit. Left : The plots report image saturation, median LightGlue confidence, number of SuperPoint–LightGlue matches, and feature coverage over a rolling window of five images. Feature coverage measures the proportion of the current frame covered by features matched and reprojected from previous images in the window. Only matches with confidence above

0.9

are retained. Solid lines and shaded regions represent the median and IQR across five repetitions. Right : BVSLAM trajectories obtained using AE and B-Adapt , together with the reference trajectory.

Fig. 6 : Effect of emulated vehicle speed on RPE RMSE . Emulated speed is computed relative to a

30\text{\,}\mathrm{Hz}

camera and increased by lowering the frame rate. Results are pooled across five repeated trajectories for each acquisition policy and frame-rate setting.

Visual SLAM

Visual simultaneous localization and mapping (SLAM) estimates camera motion while building maps from images for navigation and scene understanding.

See all 108 papers

RootSLAM: Square Root Bundle Adjustment for Visual-Inertial SLAM
Oct 10, 2026Tomás Santucci, Mateo de Mayo, Daniel Cremers +1Visual-Inertial SLAM Bundle Adjustment
National University of Rosario, Rosario, Argentina · Technical University of Munich and the Munich Center for Machine Learning, Munich, Germany · CIFASIS (CONICET-UNR), Rosario, Argentina
Smart Fusion for Adaptive Visual-IMU Weighting in cuVSLAM Sparse Bundle Adjustment
Oct 14, 2026Wonju Lee, Dara Molloy, Abhilash Nand Kumar +5Visual-Inertial SLAM Visual-Inertial Odometry
Analog Devices Inc. · NVIDIA
Why does Deep Learning Improve Visual SLAM?
Jul 7, 2026Giovanni Cioffi, Davide ScaramuzzaVisual SLAM
Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland

Oct 10, 2026J/K move · Enter open · S save

RootSLAM: Square Root Bundle Adjustment for Visual-Inertial SLAM

Tomás Santucci, Mateo de Mayo, Daniel Cremers, Taihú Pire

National University of Rosario, Rosario, Argentina · Technical University of Munich and the Munich Center for Machine Learning, Munich, Germany · CIFASIS (CONICET-UNR), Rosario, Argentina

Visual-Inertial SLAM Bundle Adjustment Pose Graph Optimization

Open paper AskPDF arXiv

Efficient perception is a prerequisite for the small, low-power devices targeted by robotics, mixed reality, autonomous driving, and drone applications, all of which rely on Simultaneous Localization and Mapping (SLAM) to estimate their motion within their surroundings. Learning-based SLAM systems achieve state-of-the-art accuracy but are demanding in compute, whereas classical geometry-based methods retain a strong efficiency advantage with little to no loss in accuracy. In this work we present RootSLAM, a fully-featured visual-inertial SLAM system for multi-camera setups built on Basalt. RootSLAM achieves accuracy competitive with the state of the art while running up to 20 times faster, facilitating the deployment of perception systems in resource constrained environments. We adapt the square-root bundle adjustment formulation from structure from motion into the multi-camera visual-inertial SLAM setting through a novel reformulation that leverages the system's pose-graph, letting the global optimizer run in single-precision floating point, thus doubling its performance. We provide a thorough benchmark against the state of the art together with an ablation study of our contributions. Our new implementation, including its map management and loop detection module, pose-graph optimizer, and global mapping components, will be open-sourced.

Abstract

Visual SLAM

Explore similar work

RootSLAM: Square Root Bundle Adjustment for Visual-Inertial SLAM

Smart Fusion for Adaptive Visual-IMU Weighting in cuVSLAM Sparse Bundle Adjustment

Why does Deep Learning Improve Visual SLAM?