paper-with-me

Papers

Evaluating geometric accuracy of NeRF reconstructions compared to SLAM method

2024-07-15 · Adam Korycki, Colleen Josephson, Steve McGuire

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.

📄 PDF Abstract BibTeX arXiv:2407.11238

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction3D Scene ReconstructionNeRF

Similar Papers 제목 키워드 기반

3D Density-Gradient based Edge Detection on Neural Radiance Fields (NeRFs) for Geometric Reconstruction

2023-09-26 · Miriam Jäger, Boris Jutzi

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 DetectionNeRFObject

PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty

2026-04-20 · Shravan Venkatraman, Rakesh Raj Madavan, Pavan Kumar Sathya Venkatesh arxiv

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

2025-11-20 · Pierrick Bournez, Luca Savant Aira, Thibaud Ehret, Gabriele Facciolo arxiv

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 Estimation

SplatSDF: Boosting Neural Implicit SDF via Gaussian Splatting Fusion

2024-11-23 · Runfa Blark Li, Keito Suzuki, Bang Du, Ki Myung Brian Le 외

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…

3DGSNeRF

A Comparative Neural Radiance Field (NeRF) 3D Analysis of Camera Poses from HoloLens Trajectories and Structure from Motion

2023-04-20 · Miriam Jäger, Patrick Hübner, Dennis Haitz, Boris Jutzi

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