# MVOFormer: Flow-Semantic Transformer for Robust Monocular Visual Odometry

arXiv: https://arxiv.org/abs/2606.16474 · HTML: https://mlsanity.com/paper/2606.16474/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [DeepV2D: Video to Depth with Differentiable Structure from Motion](https://mlsanity.com/paper/1812.04605/) (2018)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [WildGaussians: 3D Gaussian Splatting in the Wild](https://mlsanity.com/paper/2407.08447/) (2024)
- [PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation](https://mlsanity.com/paper/2306.10013/) (2023)
- [TartanVO: A Generalizable Learning-based VO](https://mlsanity.com/paper/2011.00359/) (2020)
- [Towards Better Generalization: Joint Depth-Pose Learning without PoseNet](https://mlsanity.com/paper/2004.01314/) (2020)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [LDSO: Direct Sparse Odometry with Loop Closure](https://mlsanity.com/paper/1808.01111/) (2018)
- [DiffPoseNet: Direct Differentiable Camera Pose Estimation](https://mlsanity.com/paper/2203.11174/) (2022)
- [DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments](https://mlsanity.com/paper/2209.08430/) (2022)
- [PVO: Panoptic Visual Odometry](https://mlsanity.com/paper/2207.01610/) (2022)
- [MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry](https://mlsanity.com/paper/2409.09479/) (2024)
- [NeRF-VO: Real-Time Sparse Visual Odometry with Neural Radiance Fields](https://mlsanity.com/paper/2312.13471/) (2023)
- [MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing](https://mlsanity.com/paper/2412.20082/) (2024)
- [BEV-ODOM: Reducing Scale Drift in Monocular Visual Odometry with BEV Representation](https://mlsanity.com/paper/2411.10195/) (2024)
- [Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry](https://mlsanity.com/paper/2412.16923/) (2024)

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

- [FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry](https://mlsanity.com/paper/2609.13733/) (2026)

## Abstract (arXiv)

Monocular visual odometry (MVO) is foundational to autonomous navigation and robotic localization. However, existing learning-based MVO approaches often struggle with either a lack of interpretable, complementary features or overly complex multi-stage architectures. These limitations inherently restrict their robustness and cross-domain generalization. In this work, we propose MVOFormer, a novel transformer framework for robust monocular visual odometry. Our architecture features a Flow-Semantic Dual Branch Encoder that synergizes dense geometric motion cues with object-centric semantic priors, explicitly distinguishing static structures from dynamic distractors. These representations are then fused by an Iterative Multimodal Decoder, enabling coarse-to-fine pose refinement while dynamically suppressing attention on unreliable regions. Extensive evaluations demonstrate that, without any target-domain fine-tuning, MVOFormer achieves superior zero-shot generalization and robustness, significantly outperforming prior learning-based frame-to-frame methods across diverse benchmarks including TartanAir, KITTI, TUM-RGBD, and ETH3D-SLAM.