SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction
This addresses the problem of joint optimization in 3D scene reconstruction for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the systematic sub-optimality in joint pose estimation and scene reconstruction with Neural Radiance Fields (NeRF), proposing SiNeRF with sinusoidal activations and Mixed Region Sampling to achieve significant improvements in image synthesis quality and pose estimation accuracy over NeRFmm.
NeRFmm is the Neural Radiance Fields (NeRF) that deal with Joint Optimization tasks, i.e., reconstructing real-world scenes and registering camera parameters simultaneously. Despite NeRFmm producing precise scene synthesis and pose estimations, it still struggles to outperform the full-annotated baseline on challenging scenes. In this work, we identify that there exists a systematic sub-optimality in joint optimization and further identify multiple potential sources for it. To diminish the impacts of potential sources, we propose Sinusoidal Neural Radiance Fields (SiNeRF) that leverage sinusoidal activations for radiance mapping and a novel Mixed Region Sampling (MRS) for selecting ray batch efficiently. Quantitative and qualitative results show that compared to NeRFmm, SiNeRF achieves comprehensive significant improvements in image synthesis quality and pose estimation accuracy. Codes are available at https://github.com/yitongx/sinerf.