# VOCAL: Visual Odometry via ContrAstive Learning

arXiv: https://arxiv.org/abs/2507.00243 · HTML: https://mlsanity.com/paper/2507.00243/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [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)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry](https://mlsanity.com/paper/2003.01060/) (2020)
- [Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping](https://mlsanity.com/paper/1910.02490/) (2019)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction](https://mlsanity.com/paper/1704.03489/) (2017)
- [TartanVO: A Generalizable Learning-based VO](https://mlsanity.com/paper/2011.00359/) (2020)
- [UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning](https://mlsanity.com/paper/1709.06841/) (2017)
- [MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects](https://mlsanity.com/paper/1804.09194/) (2018)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [FroDO: From Detections to 3D Objects](https://mlsanity.com/paper/2005.05125/) (2020)
- [Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling](https://mlsanity.com/paper/2007.10983/) (2020)
- [DSP-SLAM: Object Oriented SLAM with Deep Shape Priors](https://mlsanity.com/paper/2108.09481/) (2021)
- [DF-VO: What Should Be Learnt for Visual Odometry?](https://mlsanity.com/paper/2103.00933/) (2021)
- [PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning](https://mlsanity.com/paper/2105.05643/) (2021)

## Abstract (arXiv)

Breakthroughs in visual odometry (VO) have fundamentally reshaped the landscape of robotics, enabling ultra-precise camera state estimation that is crucial for modern autonomous systems. Despite these advances, many learning-based VO techniques rely on rigid geometric assumptions, which often fall short in interpretability and lack a solid theoretical basis within fully data-driven frameworks. To overcome these limitations, we introduce VOCAL (Visual Odometry via ContrAstive Learning), a novel framework that reimagines VO as a label ranking challenge. By integrating Bayesian inference with a representation learning framework, VOCAL organizes visual features to mirror camera states. The ranking mechanism compels similar camera states to converge into consistent and spatially coherent representations within the latent space. This strategic alignment not only bolsters the interpretability of the learned features but also ensures compatibility with multimodal data sources. Extensive evaluations on the KITTI dataset highlight VOCAL's enhanced interpretability and flexibility, pushing VO toward more general and explainable spatial intelligence.