# ViBA: Implicit Bundle Adjustment with Geometric and Temporal Consistency for Robust Visual Matching

arXiv: https://arxiv.org/abs/2604.03377 · HTML: https://mlsanity.com/paper/2604.03377/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [BA-Net: Dense Bundle Adjustment Network](https://mlsanity.com/paper/1806.04807/) (2018)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences](https://mlsanity.com/paper/1912.05524/) (2019)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation](https://mlsanity.com/paper/2304.03608/) (2023)
- [DeepFactors: Real-Time Probabilistic Dense Monocular SLAM](https://mlsanity.com/paper/2001.05049/) (2020)
- [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024)
- [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021)
- [GIM: Learning Generalizable Image Matcher From Internet Videos](https://mlsanity.com/paper/2402.11095/) (2024)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics](https://mlsanity.com/paper/2407.10648/) (2024)
- [DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features](https://mlsanity.com/paper/2008.05416/) (2020)
- [Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares](https://mlsanity.com/paper/2305.09527/) (2023)
- [ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization](https://mlsanity.com/paper/2203.03610/) (2022)
- [Breaking of brightness consistency in optical flow with a lightweight CNN network](https://mlsanity.com/paper/2310.15655/) (2023)
- [DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing](https://mlsanity.com/paper/2401.09160/) (2024)

## Built on by (most cited first, 1 of 1)

- [MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle Adjustment](https://mlsanity.com/paper/2609.13691/) (2026)

## Abstract (arXiv)

Most existing image keypoint detection and description methods rely on datasets with accurate pose and depth annotations, limiting scalability and generalization, and often degrading navigation and localization performance. We propose ViBA, a sustainable learning framework that integrates geometric optimization with feature learning for continuous online training on unconstrained video streams. Embedded in a standard visual odometry pipeline, it consists of an implicitly differentiable geometric residual framework: (i) an initial tracking network for inter-frame correspondences, (ii) depth-based outlier filtering, and (iii) differentiable global bundle adjustment that jointly refines camera poses and feature positions by minimizing reprojection errors. By combining geometric consistency from BA with long-term temporal consistency across frames, ViBA enforces stable and accurate feature representations. We evaluate ViBA on EuRoC and UMA datasets. Compared with state-of-the-art methods such as SuperPoint+SuperGlue, ALIKED, and LightGlue, ViBA reduces mean absolute translation error (ATE) by 12-18% and absolute rotation error (ARE) by 5-10% across sequences, while maintaining real-time inference speeds (FPS 36-91). When evaluated on unseen sequences, it retains over 90% localization accuracy, demonstrating robust generalization. These results show that ViBA supports continuous online learning with geometric and temporal consistency, consistently improving navigation and localization in real-world scenarios.