Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report

• URL: http://arxiv.org/abs/2211.04470v1
• Date: Mon, 7 Nov 2022 22:20:07 GMT
• Title: Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report
• Authors: Andrey Ignatov and Grigory Malivenko and Radu Timofte and Lukasz Treszczotko and Xin Chang and Piotr Ksiazek and Michal Lopuszynski and Maciej Pioro and Rafal Rudnicki and Maciej Smyl and Yujie Ma and Zhenyu Li and Zehui Chen and Jialei Xu and Xianming Liu and Junjun Jiang and XueChao Shi and Difan Xu and Yanan Li and Xiaotao Wang and Lei Lei and Ziyu Zhang and Yicheng Wang and Zilong Huang and Guozhong Luo and Gang Yu and Bin Fu and Jiaqi Li and Yiran Wang and Zihao Huang and Zhiguo Cao and Marcos V. Conde and Denis Sapozhnikov and Byeong Hyun Lee and Dongwon Park and Seongmin Hong and Joonhee Lee and Seunggyu Lee and Se Young Chun
• Abstract summary: Deep learning-based single image depth estimation solutions can show a real-time performance on IoT platforms and smartphones. Models developed in the challenge are also compatible with any Android or Linux-based mobile devices.
• Score: 108.88637766066759
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper.

Related papers

• Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report [75.79829464552311]
  This challenge was to develop an efficient end-to-end AI-based rendering approach that can run on modern smartphone models. The resulting model was evaluated on the Kirin 9000's Mali GPU that provides excellent acceleration results for the majority of common deep learning ops.
  arXiv  Detail & Related papers  (2022-11-07T22:42:02Z)
• Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report [65.91472671013302]
  We introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions. The proposed solutions are fully compatible with all major mobile AI accelerators and can demonstrate more than 100-200 FPS on the majority of recent smartphone platforms.
  arXiv  Detail & Related papers  (2021-05-17T13:55:38Z)
• Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report [105.32612705754605]
  We introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solution. The proposed solutions can generate VGA resolution depth maps at up to 10 FPS on the Raspberry Pi 4 while achieving high fidelity results.
  arXiv  Detail & Related papers  (2021-05-17T13:49:57Z)
• Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report [64.09439666916465]
  We introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image denoising solution. The proposed solutions are fully compatible with any mobile GPU and are capable of processing 480p resolution images under 40-80 ms.
  arXiv  Detail & Related papers  (2021-05-17T13:27:56Z)
• Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report [49.643297263102845]
  This challenge aims to develop an end-to-end deep learning-based image signal processing pipeline. The proposed solutions are capable of processing Full HD photos under 60-100 milliseconds while achieving high fidelity results.
  arXiv  Detail & Related papers  (2021-05-17T13:20:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.