Name
Title | ||
|---|---|---|
Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report |
Abstract | ||
|---|---|---|
Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms. For this, the participants were provided with a new large-scale dataset containing RGB-depth image pairs obtained with a dedicated stereo ZED camera producing high-resolution depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the popular Raspberry Pi 4 platform with a mobile ARM-based Broadcom chipset. The proposed solutions can generate VGA resolution depth maps at up to 10 FPS on the Raspberry Pi 4 while achieving high fidelity results, and are compatible with any Android or Linux-based mobile devices. A detailed description of all models developed in the challenge is provided in this paper. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/CVPRW53098.2021.00288 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 21 | 38 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Andrey Ignatov | 1 | 30 | 6.66 |
| Grigory Malivenko | 2 | 0 | 0.68 |
| David Plowman | 3 | 0 | 0.34 |
| Samarth Shukla | 4 | 0 | 0.68 |
| Radu Timofte | 5 | 1880 | 118.45 |
| Ziyu Zhang | 6 | 112 | 10.19 |
| Yicheng Wang | 7 | 22 | 8.06 |
| Zilong Huang | 8 | 0 | 0.68 |
| Guozhong Luo | 9 | 0 | 1.01 |
| Gang Yu | 10 | 382 | 19.85 |
| Bin Fu | 11 | 0 | 0.68 |
| Yiran Wang | 12 | 0 | 1.01 |
| Xingyi Li | 13 | 17 | 4.19 |
| Min Shi | 14 | 0 | 1.35 |
| Ke Xian | 15 | 55 | 8.99 |
| Zhiguo Cao | 16 | 314 | 44.17 |
| Jin-Hua Du | 17 | 0 | 0.68 |
| Pei-Lin Wu | 18 | 0 | 0.68 |
| Chao Ge | 19 | 0 | 0.68 |
| Jiaoyang Yao | 20 | 0 | 0.34 |
| Fangwen Tu | 21 | 0 | 0.34 |
| Bo Li | 22 | 0 | 0.34 |
| Jung Eun Yoo | 23 | 0 | 0.34 |
| Kwanggyoon Seo | 24 | 0 | 0.68 |
| Jialei Xu | 25 | 0 | 0.34 |
| Zhenyu Li | 26 | 0 | 1.69 |
| Xianming Liu | 27 | 461 | 47.55 |
| Junjun Jiang | 28 | 1138 | 74.49 |
| Wei-Chi Chen | 29 | 0 | 0.34 |
| Shayan Joya | 30 | 0 | 0.34 |
| Huanhuan Fan | 31 | 0 | 0.68 |
| Zhaobing Kang | 32 | 0 | 0.34 |
| Ang Li | 33 | 0 | 1.01 |
| Tianpeng Feng | 34 | 0 | 0.34 |
| Yang Liu | 35 | 0 | 0.34 |
| Chuannan Sheng | 36 | 0 | 0.34 |
| Jian Yin | 37 | 0 | 0.34 |
| Fausto T. Benavide | 38 | 0 | 0.34 |