DINO-VO: Learning Where to Focus for Enhanced State Estimation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915917318848512 |
|---|---|
| author | Chen, Qi Li, Guanghao Hu, Sijia Gao, Xin Ma, Junpeng Xue, Xiangyang Pu, Jian |
| author_facet | Chen, Qi Li, Guanghao Hu, Sijia Gao, Xin Ma, Junpeng Xue, Xiangyang Pu, Jian |
| contents | We present DINO Patch Visual Odometry (DINO-VO), an end-to-end monocular visual odometry system with strong scene generalization. Current Visual Odometry (VO) systems often rely on heuristic feature extraction strategies, which can degrade accuracy and robustness, particularly in large-scale outdoor environments. DINO-VO addresses these limitations by incorporating a differentiable adaptive patch selector into the end-to-end pipeline, improving the quality of extracted patches and enhancing generalization across diverse datasets. Additionally, our system integrates a multi-task feature extraction module with a differentiable bundle adjustment (BA) module that leverages inverse depth priors, enabling the system to learn and utilize appearance and geometric information effectively. This integration bridges the gap between feature learning and state estimation. Extensive experiments on the TartanAir, KITTI, Euroc, and TUM datasets demonstrate that DINO-VO exhibits strong generalization across synthetic, indoor, and outdoor environments, achieving state-of-the-art tracking accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04055 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DINO-VO: Learning Where to Focus for Enhanced State Estimation Chen, Qi Li, Guanghao Hu, Sijia Gao, Xin Ma, Junpeng Xue, Xiangyang Pu, Jian Computer Vision and Pattern Recognition Robotics We present DINO Patch Visual Odometry (DINO-VO), an end-to-end monocular visual odometry system with strong scene generalization. Current Visual Odometry (VO) systems often rely on heuristic feature extraction strategies, which can degrade accuracy and robustness, particularly in large-scale outdoor environments. DINO-VO addresses these limitations by incorporating a differentiable adaptive patch selector into the end-to-end pipeline, improving the quality of extracted patches and enhancing generalization across diverse datasets. Additionally, our system integrates a multi-task feature extraction module with a differentiable bundle adjustment (BA) module that leverages inverse depth priors, enabling the system to learn and utilize appearance and geometric information effectively. This integration bridges the gap between feature learning and state estimation. Extensive experiments on the TartanAir, KITTI, Euroc, and TUM datasets demonstrate that DINO-VO exhibits strong generalization across synthetic, indoor, and outdoor environments, achieving state-of-the-art tracking accuracy. |
| title | DINO-VO: Learning Where to Focus for Enhanced State Estimation |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2604.04055 |