Invertible Neural Warp for NeRF
This addresses the problem of simultaneous pose and scene reconstruction for 3D computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the joint optimization of camera poses and Neural Radiance Fields (NeRF) by proposing a novel overparameterized representation using learnable rigid warp functions, and it demonstrates improved pose estimation and reconstruction quality on synthetic and real-world datasets.
This paper tackles the simultaneous optimization of pose and Neural Radiance Fields (NeRF). Departing from the conventional practice of using explicit global representations for camera pose, we propose a novel overparameterized representation that models camera poses as learnable rigid warp functions. We establish that modeling the rigid warps must be tightly coupled with constraints and regularization imposed. Specifically, we highlight the critical importance of enforcing invertibility when learning rigid warp functions via neural network and propose the use of an Invertible Neural Network (INN) coupled with a geometry-informed constraint for this purpose. We present results on synthetic and real-world datasets, and demonstrate that our approach outperforms existing baselines in terms of pose estimation and high-fidelity reconstruction due to enhanced optimization convergence.