Deep Patch Visual Odometry
We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for monocular Visual Odometry (VO). DPVO uses a novel recurrent network architecture designed for tracking image patches across time. Recent approaches to VO have significantly improved the state-of-the-art accuracy by using deep networks to predict dense flow between video frames. However, using dense flow incurs a large computational cost, making these previous methods impractical for many use cases. Despite this, it has been assumed that dense flow is important as it provides additional redundancy against incorrect matches. DPVO disproves this assumption, showing that it is possible to get the best accuracy and efficiency by exploiting the advantages of sparse patch-based matching over dense flow. DPVO introduces a novel recurrent update operator for patch based correspondence coupled with differentiable bundle adjustment. On Standard benchmarks, DPVO outperforms all prior work, including the learning-based state-of-the-art VO-system (DROID) using a third of the memory while running 3x faster on average. Code is available at https://github.com/princeton-vl/DPVO
Code (1)
Tasks
Monocular Visual OdometryVisual OdometrySimilar Papers 제목 키워드 기반
Extending Deep Event Visual Odometry with Sparse Point-Cloud Export
Event cameras are well suited for visual odometry under high-speed motion and challenging lighting conditions due to their low latency, high temporal resolution, and high dynamic range. Deep Event Visual Odometry (DEVO) …
Visual OdometryPhysical Passive Patch Adversarial Attacks on Visual Odometry Systems
Deep neural networks are known to be susceptible to adversarial perturbations -- small perturbations that alter the output of the network and exist under strict norm limitations. While such perturbations are usually disc…
Autonomous NavigationDrone navigationVisual OdometryDINO-VO: Learning Where to Focus for Enhanced State Estimation
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…
Visual OdometryDPVO-QAT++: Heterogeneous QAT and CUDA Kernel Fusion for High-Performance Deep Patch Visual Odometry
Deep learning-based Visual SLAM (vSLAM) systems exhibit exceptional geometric reasoning capabilities, yet their prohibitive computational overhead severely restricts deployment on resource-constrained autonomous platform…
Visual OdometryRobust Monocular Visual Odometry using Curriculum Learning
Curriculum Learning (CL), drawing inspiration from natural learning patterns observed in humans and animals, employs a systematic approach of gradually introducing increasingly complex training data during model developm…
Monocular Visual OdometryRobot NavigationSchedulingVisual Odometry