NeRF-VO: Real-Time Sparse Visual Odometry with Neural Radiance Fields
This work addresses the problem of efficient and accurate 3D scene understanding for robotics and AR/VR applications, representing an incremental improvement by combining existing methods in a novel way.
The paper tackles real-time monocular visual odometry and dense scene reconstruction by integrating sparse visual odometry with neural radiance fields, achieving state-of-the-art performance in pose accuracy, novel view synthesis, and reconstruction quality across synthetic and real-world datasets.
We introduce a novel monocular visual odometry (VO) system, NeRF-VO, that integrates learning-based sparse visual odometry for low-latency camera tracking and a neural radiance scene representation for fine-detailed dense reconstruction and novel view synthesis. Our system initializes camera poses using sparse visual odometry and obtains view-dependent dense geometry priors from a monocular prediction network. We harmonize the scale of poses and dense geometry, treating them as supervisory cues to train a neural implicit scene representation. NeRF-VO demonstrates exceptional performance in both photometric and geometric fidelity of the scene representation by jointly optimizing a sliding window of keyframed poses and the underlying dense geometry, which is accomplished through training the radiance field with volume rendering. We surpass SOTA methods in pose estimation accuracy, novel view synthesis fidelity, and dense reconstruction quality across a variety of synthetic and real-world datasets while achieving a higher camera tracking frequency and consuming less GPU memory.