Evaluating geometric accuracy of NeRF reconstructions compared to SLAM method
As Neural Radiance Field (NeRF) implementations become faster, more efficient and accurate, their applicability to real world mapping tasks becomes more accessible. Traditionally, 3D mapping, or scene reconstruction, has relied on expensive LiDAR sensing. Photogrammetry can perform image-based 3D reconstruction but is computationally expensive and requires extremely dense image representation to recover complex geometry and photorealism. NeRFs perform 3D scene reconstruction by training a neural network on sparse image and pose data, achieving superior results to photogrammetry with less input data. This paper presents an evaluation of two NeRF scene reconstructions for the purpose of estimating the diameter of a vertical PVC cylinder. One of these are trained on commodity iPhone data and the other is trained on robot-sourced imagery and poses. This neural-geometry is compared to state-of-the-art lidar-inertial SLAM in terms of scene noise and metric-accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Reconstruction3D Scene ReconstructionNeRFSimilar Papers 제목 키워드 기반
3D Density-Gradient based Edge Detection on Neural Radiance Fields (NeRFs) for Geometric Reconstruction
Generating geometric 3D reconstructions from Neural Radiance Fields (NeRFs) is of great interest. However, accurate and complete reconstructions based on the density values are challenging. The network output depends on …
Edge DetectionNeRFObjectPCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty
Neural surface reconstruction methods typically treat camera poses as fixed values, assuming perfect accuracy from Structure-from-Motion (SfM) systems. This assumption breaks down with imperfect pose estimates, leading t…
EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering
Recently, 3D Gaussian Splatting has been introduced as a compelling alternative to NeRF for Earth observation, offering competitive reconstruction quality with significantly reduced training times. In this work, we exten…
Camera Pose EstimationSplatSDF: Boosting Neural Implicit SDF via Gaussian Splatting Fusion
A signed distance function (SDF) is a useful representation for continuous-space geometry and many related operations, including rendering, collision checking, and mesh generation. Hence, reconstructing SDF from image ob…
3DGSNeRFA Comparative Neural Radiance Field (NeRF) 3D Analysis of Camera Poses from HoloLens Trajectories and Structure from Motion
Neural Radiance Fields (NeRFs) are trained using a set of camera poses and associated images as input to estimate density and color values for each position. The position-dependent density learning is of particular inter…
3D ReconstructionNeRFPosition