Abstract | ||
---|---|---|
We present a benchmark for image-based 3D reconstruction. The benchmark sequences were acquired outside the lab, in realistic conditions. Ground-truth data was captured using an industrial laser scanner. The benchmark includes both outdoor scenes and indoor environments. High-resolution video sequences are provided as input, supporting the development of novel pipelines that take advantage of video input to increase reconstruction fidelity. We report the performance of many image-based 3D reconstruction pipelines on the new benchmark. The results point to exciting challenges and opportunities for future work. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3072959.3073599 | ACM Trans. Graph. |
Keywords | Field | DocType |
Structure from motion,multi-view stereo,image-based reconstruction,large-scale scene reconstruction | Structure from motion,Computer vision,Pipeline transport,Fidelity,Laser scanning,Computer graphics (images),Artificial intelligence,Mathematics,Benchmarking,3D reconstruction | Journal |
Volume | Issue | ISSN |
36 | 4 | 0730-0301 |
Citations | PageRank | References |
65 | 1.74 | 38 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arno Knapitsch | 1 | 65 | 1.74 |
Jaesik Park | 2 | 496 | 24.88 |
Qian-Yi Zhou | 3 | 763 | 26.88 |
Vladlen Koltun | 4 | 4064 | 162.63 |