CVApr 2, 2025

FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking

arXiv:2504.01732v25 citationsh-index: 46SCIA
Originality Synthesis-oriented
AI Analysis

This dataset addresses scalability issues for researchers in 3D scene reconstruction and novel view synthesis, though it is incremental as it extends existing methods with new data.

The authors tackled the problem of limited scalability in 3D scene reconstruction due to narrow-field-of-view datasets by introducing a fisheye image dataset with 5 indoor and 5 outdoor scenes, providing full 360-degree coverage and precise LIDAR ground truth for robust benchmarking.

The development of large-scale 3D scene reconstruction and novel view synthesis methods mostly rely on datasets comprising perspective images with narrow fields of view (FoV). While effective for small-scale scenes, these datasets require large image sets and extensive structure-from-motion (SfM) processing, limiting scalability. To address this, we introduce a fisheye image dataset tailored for scene reconstruction tasks. Using dual 200-degree fisheye lenses, our dataset provides full 360-degree coverage of 5 indoor and 5 outdoor scenes. Each scene has sparse SfM point clouds and precise LIDAR-derived dense point clouds that can be used as geometric ground-truth, enabling robust benchmarking under challenging conditions such as occlusions and reflections. While the baseline experiments focus on vanilla Gaussian Splatting and NeRF based Nerfacto methods, the dataset supports diverse approaches for scene reconstruction, novel view synthesis, and image-based rendering.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes