PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment
For robotics and AR/VR applications requiring metric-scale visual odometry from a single sensor, PRISM-VO provides a drift-resilient, purely optimization-based solution that avoids complex initialization.
PRISM-VO introduces a sparse photometric visual odometry framework for plenoptic cameras that jointly optimizes poses and inverse depths via bundle adjustment, achieving accurate metric-scale motion estimation. It outperforms the state-of-the-art plenoptic VO method on indoor and outdoor scenes, rivaling optimization- and learning-based approaches.
We introduce PRISM-VO, a novel pure optimization-based sparse photometric visual odometry framework for focused plenoptic cameras. The core of PRISM-VO is a novel photometric plenoptic bundle adjustment which jointly optimizes camera poses and inverse depth values of points in a sliding window. By combining geometric depth from a single plenoptic image with temporal multi-view constraints, PRISM-VO achieves accurate and drift-resilient motion estimation. Through explicit modeling of the plenoptic projection, PRISM-VO provides reliable metric-scale reconstructions, overcoming the scale ambiguity of monocular SLAM algorithms. Importantly, our approach relies solely on a single plenoptic sensor and avoids complex initialization, as depth priors are computed directly from plenoptic imaging. Experiments show that PRISM-VO outperforms the current state-of-the-art plenoptic visual odometry method on indoor and outdoor scenes. The proposed approach rivals other optimization- and learning-based methods while accurately and reliably recovering a metric scale of the scene. Project page: https://prism-vo.github.io/