Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
This work improves camera pose estimation for applications like augmented reality, though it is incremental as it builds on existing APR methods.
The authors tackled camera relocalization by combining absolute pose regression with a photometric consistency module, achieving state-of-the-art accuracy on the 7-Scenes and LLFF benchmarks.
We present a relocalization pipeline, which combines an absolute pose regression (APR) network with a novel view synthesis based direct matching module, offering superior accuracy while maintaining low inference time. Our contribution is twofold: i) we design a direct matching module that supplies a photometric supervision signal to refine the pose regression network via differentiable rendering; ii) we modify the rotation representation from the classical quaternion to SO(3) in pose regression, removing the need for balancing rotation and translation loss terms. As a result, our network Direct-PoseNet achieves state-of-the-art performance among all other single-image APR methods on the 7-Scenes benchmark and the LLFF dataset.