NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations
This dataset addresses a bottleneck for researchers in 3D reconstruction and correspondence estimation by providing systematic benchmarks for casual image captures.
The authors tackled the lack of high-quality ground-truth camera poses for 3D reconstruction from in-the-wild image collections by introducing NAVI, a dataset with category-agnostic image collections, 3D scans, and near-perfect camera parameters, enabling more thorough evaluations.
Recent advances in neural reconstruction enable high-quality 3D object reconstruction from casually captured image collections. Current techniques mostly analyze their progress on relatively simple image collections where Structure-from-Motion (SfM) techniques can provide ground-truth (GT) camera poses. We note that SfM techniques tend to fail on in-the-wild image collections such as image search results with varying backgrounds and illuminations. To enable systematic research progress on 3D reconstruction from casual image captures, we propose NAVI: a new dataset of category-agnostic image collections of objects with high-quality 3D scans along with per-image 2D-3D alignments providing near-perfect GT camera parameters. These 2D-3D alignments allow us to extract accurate derivative annotations such as dense pixel correspondences, depth and segmentation maps. We demonstrate the use of NAVI image collections on different problem settings and show that NAVI enables more thorough evaluations that were not possible with existing datasets. We believe NAVI is beneficial for systematic research progress on 3D reconstruction and correspondence estimation. Project page: https://navidataset.github.io