Carview!

CARVIEW

MOTORHOMES

Select Language

HTTP/2 301 server: GitHub.com content-type: text/html location: https://albert100121.github.io/AiFDepthNet/ x-github-request-id: 44CE:234FE9:98D21E:AB896A:695335D6 accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 02:15:50 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210095-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767060951.526128,VS0,VE198 vary: Accept-Encoding x-fastly-request-id: 93864c6a3dbc12724d81bae04f443b0af4c07035 content-length: 162 HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Thu, 06 Jan 2022 09:42:29 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"61d6b985-2d0a" expires: Tue, 30 Dec 2025 02:25:50 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 12CD:2685F2:967723:A92DD6:695335D5 accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 02:15:50 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210095-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767060951.737567,VS0,VE217 vary: Accept-Encoding x-fastly-request-id: e9fb2039b085a5119f2bacd080f6fe9333e03824 content-length: 3155 Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision

Abstract

Depth estimation is a long-lasting yet important task in computer vision. Most of the previous works try to estimate depth from input images and assume images are all-in-focus (AiF), which is less common in real-world applications. On the other hand, a few works take defocus blur into account and consider it as another cue for depth estimation. In this paper, we propose a method to estimate not only a depth map but an AiF image from a set of images with different focus positions (known as a focal stack). We design a shared architecture to exploit the relationship between depth and AiF estimation. As a result, the proposed method can be trained either supervisedly with ground truth depth, or unsupervisedly with AiF images as supervisory signals. We show in various experiments that our method outperforms the state-of-the-art methods both quantitatively and qualitatively, and also has higher efficiency in inference time.

Video

Paper

ICCV 2021 (arXiv)

Supplementary

Poster

Citation

Ning-Hsu Wang, Ren Wang, Yu-Lun Liu, Yu-Hao Huang, Yu-Lin Chang, Chia-Ping Chen, Kevin Jou, "Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision", in International Conference on Computer Vision (ICCV), 2021

Bibtex

@inproceedings{Wang-ICCV-2021,
      author    = {Wang, Ning-Hsu and Wang, Ren and Liu, Yu-Lun and Huang, Yu-Hao and Chang, Yu-Lin and Chen, Chia-Ping and Jou, Kevin}, 
      title     = {Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision}, 
      booktitle = {IEEE International Conference on Computer Vision},
      year      = {2021}
  }

Download