In this supplementary material, we provide additional implementation details (Appendix A) of our model and visualization of ablation studies (Appendix B) which are not included in our main paper. BARF-W, and BARF-WD are based on [2] because there is no official NeRF-W code available. The detailed architecture of UP-NeRF is shown in the Figure 1. First two authors have an equal contribution. As we mentioned in the main paper, the evaluation process entails two stages, which are test-time pose optimization and appearance optimization.

Which allows to conclude that the sigmoid corresponds to the Heaviside function perturbed with a logistic noise. As introduced in the paper, control variates methods can be used to reduce the noise of the Monte-Carlo estimators of the Jacobian of a perturbed renderer, without inducing any extra-computation. Proposition 5. Jacobian of perturbed renderers can be written as: J We adapt the previous proof to the case of a Cauchy distribution for the noise. Z 1 (67) remains valid. Z 1 (73) 17 Figure 9: Pose optimization with an initial guess uniformly sampled on the rotation space.

Visual localization is a fundamental task in computer vision and robotics.

So they have difficulty handling unconstrained images with varying illumination and transient occluders.

Efficient and accurate camera pose estimation forms the foundational requirement for dense reconstruction in autonomous navigation, robotic perception, and virtual simulation systems. This paper addresses the challenge via cuSfM, a CUDA-accelerated offline Structure-from-Motion system that leverages GPU parallelization to efficiently employ computationally intensive yet highly accurate feature extractors, generating comprehensive and non-redundant data associations for precise camera pose estimation and globally consistent mapping. The system supports pose optimization, mapping, prior-map localization, and extrinsic refinement. It is designed for offline processing, where computational resources can be fully utilized to maximize accuracy. Experimental results demonstrate that cuSfM achieves significantly improved accuracy and processing speed compared to the widely used COLMAP method across various testing scenarios, while maintaining the high precision and global consistency essential for offline SfM applications. The system is released as an open-source Python wrapper implementation, PyCuSfM, available at https://github.com/nvidia-isaac/pyCuSFM, to facilitate research and applications in computer vision and robotics.

Visual localization is a fundamental task in computer vision and robotics.

The tracking module of a visual-inertial SLAM system processes incoming image frames and IMU data to estimate the position of the frame in relation to the map. It is important for the tracking to complete in a timely manner for each frame to avoid poor localization or tracking loss. We therefore present a new approach which leverages GPU computing power to accelerate time-consuming components of tracking in order to improve its performance. These components include stereo feature matching and local map tracking. We implement our design inside the ORB-SLAM3 tracking process using CUDA. Our evaluation demonstrates an overall improvement in tracking performance of up to 2.8x on a desktop and Jetson Xavier NX board in stereo-inertial mode, using the well-known SLAM datasets EuRoC and TUM-VI.