DINO-VO: Learning Where to Focus for Enhanced State Estimation

• URL: http://arxiv.org/abs/2604.04055v1
• Date: Sun, 05 Apr 2026 10:59:48 GMT
• Title: DINO-VO: Learning Where to Focus for Enhanced State Estimation
• Abstract summary: We present DINO Patch Visual Odometry (DINO-VO), an end-to-end monocular odometry system with strong scene generalization.<n>DINO-VO addresses limitations by incorporating a differentiable adaptive patch selector into the end-to-end pipeline.<n>Experiments on the TartanAir, KITTI, Euroc, and TUM datasets demonstrate that DINO-VO exhibits strong generalization across synthetic, indoor, and outdoor environments.
• Score: 44.599349414955014
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data [0.0]
  We introduce depth as a geometric prior during training in learning more robust latent dynamics directly from robot video data.<n>We evaluate with frozen-representation visual odometry probes, predictor-based surprise detection, and multi-step latent rollout fidelity.<n>Results show that a lightweight training-time geometric prior makes a compact JEPA world model more useful and more transferable on real outdoor data.
  arXiv  Detail & Related papers  (2026-07-15T00:58:45Z)
• Enhancing Eye Feature Estimation from Event Data Streams through Adaptive Inference State Space Modeling [68.1289208938377]
  Eye feature extraction from event-based data streams can be performed efficiently and with low energy consumption.<n>We introduce the emphadaptive inference state space model (AISSM), a novel architecture for feature extraction.<n>We also craft and evaluate a novel learning technique that improves training efficiency.
  arXiv  Detail & Related papers  (2026-03-14T18:47:08Z)
• DiveUp: Learning Feature Upsampling from Diverse Vision Foundation Models [11.659303031631723]
  DiveUp is a novel framework that breaks away from single-model dependency by introducing multi-VFM relational guidance.<n>We propose a universal relational feature representation, formulated as a local center-of-mass (COM) field, that extracts intrinsic geometric structures.<n>DiveUp is a unified, encoder-agnostic framework; a jointly-trained model can universally upsample features from diverse VFMs.
  arXiv  Detail & Related papers  (2026-03-13T20:20:22Z)
• VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection [10.895746797423223]
  We introduce a Geometry-guided virtual Outlier Synthesis (GOS) strategy that models statistical properties using the von Mises-Fisher (vMF) distribution on a hypersphere.<n>Specifically, we locate a low-likelihood annulus in the feature space and perform directional sampling of virtual outliers in this region.<n>Experiments on benchmarks such as CIFAR-LT demonstrate that our method outperforms sota approaches that utilize external real images.
  arXiv  Detail & Related papers  (2026-02-05T07:58:12Z)
• Visual Odometry with Transformers [68.453547770334]
  We introduce Visual odometry Transformer (VoT), which processes sequences of monocular frames by extracting features.<n>Unlike prior methods, VoT directly predicts camera motion without estimating dense geometry and relies solely on camera poses for supervision.<n>VoT scales effectively with larger datasets, benefits substantially from stronger pre-trained backbones, generalizes across diverse camera motions and calibration settings, and outperforms traditional methods while running more than 3 times faster.
  arXiv  Detail & Related papers  (2025-10-02T17:00:14Z)
• DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model [2.163881720692685]
  Learning-based monocular visual odometry (VO) poses robustness, generalization, and efficiency challenges in robotics.<n>Recent advances in visual foundation models, such as DINOv2, have improved robustness and generalization in various vision tasks.<n>We present DINO-VO, a feature-based VO system leveraging DINOv2 visual foundation model for its sparse feature matching.
  arXiv  Detail & Related papers  (2025-07-17T14:09:34Z)
• BRIGHT-VO: Brightness-Guided Hybrid Transformer for Visual Odometry with Multi-modality Refinement Module [11.898515581215708]
  Visual odometry (VO) plays a crucial role in autonomous driving, robotic navigation, and other related tasks.<n>We introduce BrightVO, a novel VO model based on Transformer architecture, which performs front-end visual feature extraction.<n>Using pose graph optimization, this module iteratively refines pose estimates to reduce errors and improve both accuracy and robustness.
  arXiv  Detail & Related papers  (2025-01-15T08:50:52Z)
• PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection [59.355022416218624]
  integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. We propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN) PVAFN uses a multi-pooling strategy to integrate both multi-scale and region-specific information effectively.
  arXiv  Detail & Related papers  (2024-08-26T19:43:01Z)
• LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry [53.5449912019877]
  We present the Long-term Effective Any Point Tracking (LEAP) module.<n>LEAP innovatively combines visual, inter-track, and temporal cues with mindfully selected anchors for dynamic track estimation.<n>Based on these traits, we develop LEAP-VO, a robust visual odometry system adept at handling occlusions and dynamic scenes.
  arXiv  Detail & Related papers  (2024-01-03T18:57:27Z)
• Robust Visual Odometry Using Position-Aware Flow and Geometric Bundle Adjustment [16.04240592057438]
  A novel optical flow network (PANet) built on a position-aware mechanism is proposed first. Then, a novel system that jointly estimates depth, optical flow, and ego-motion without a typical network to learning ego-motion is proposed. Experiments show that the proposed system not only outperforms other state-of-the-art methods in terms of depth, flow, and VO estimation.
  arXiv  Detail & Related papers  (2021-11-22T12:05:27Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.