NeRFの並列逆最適化によるロバストなカメラ姿勢推定
Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation
高速NeRFと並列モンテカルロサンプリングを組み合わせ、単一RGB画像から物体やシーンに対するカメラの6自由度姿勢を高精度かつロバストに推定する手法を提案した。
著者: Yunzhi Lin, Thomas Müller, Jonathan Tremblay, Bowen Wen, Stephen Tyree, Alex Evans, Patricio A. Vela, Stan Birchfield
分類: cs.CV, cs.RO
原文アブストラクト
We present a parallelized optimization method based on fast Neural Radiance Fields (NeRF) for estimating 6-DoF pose of a camera with respect to an object or scene. Given a single observed RGB image of the target, we can predict the translation and rotation of the camera by minimizing the residual between pixels rendered from a fast NeRF model and pixels in the observed image. We integrate a momentum-based camera extrinsic optimization procedure into Instant Neural Graphics Primitives, a recent exceptionally fast NeRF implementation. By introducing parallel Monte Carlo sampling into the pose estimation task, our method overcomes local minima and improves efficiency in a more extensive search space. We also show the importance of adopting a more robust pixel-based loss function to reduce error. Experiments demonstrate that our method can achieve improved generalization and robustness on both synthetic and real-world benchmarks.
