Synthetic depth-of-field with a single-camera mobile phone
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
Shallow depth-of-field is commonly used by photographers to isolate a subject from a distracting background. However, standard cell phone cameras cannot produce such images optically, as their short focal lengths and small apertures capture nearly all-in-focus images. We present a system to computationally synthesize shallow depth-of-field images with a single mobile camera and a single button press. If the image is of a person, we use a person segmentation network to separate the person and their accessories from the background. If available, we also use dense dual-pixel auto-focus hardware, effectively a 2-sample light field with an approximately 1 millimeter baseline, to compute a dense depth map. These two signals are combined and used to render a defocused image. Our system can process a 5.4 megapixel image in 4 seconds on a mobile phone, is fully automatic, and is robust enough to be used by non-experts. The modular nature of our system allows it to degrade naturally in the absence of a dual-pixel sensor or a human subject.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408 · cited 1×
“Our implementation is in Tensorflow [Abadi et al. 2015].”
MethodA Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
Scharstein, D., & Szeliski, R. (2002) · International Journal of Computer Vision · doi:10.1023/a:1014573219977 · Cited by 6,740 · cited 1×
“Depth estimation from stereo has been the subject of extensive work (well-surveyed in [Scharstein and Szeliski 2002]).”
MethodStacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634 · cited 1×
“Given the training set, we use a network architecture consisting of 3 stacked U-Nets [Ronneberger et al. 2015] with intermediate supervision after each stage similar to Newell et al. [2016] (Fig.”
MethodLevoy, M., & Hanrahan, P. (1996) · Proceedings of the 23rd annual conference on Computer graphics and interactive techniques · doi:10.1145/237170.237199 · Cited by 3,755 · cited 1×
“DPsensors effectively create a crude, two-view light field [Gortler et al. 1996; Levoy and Hanrahan 1996] the mobile camera’s aperture ( 1 mm).”
BackgroundSelf-citationSpatiotemporal energy models for the perception of motion
Adelson, E. H., & Bergen, J. R. (1985) · Journal of the Optical Society of America A · doi:10.1364/josaa.2.000284 · Cited by 3,442 · cited 1×
“For our purely horizontal matching problem the vertical gradients are not informative, due to the aperture problem [Adelson and Bergen 1985].”
BackgroundDepth Map Prediction from a Single Image using a Multi-Scale Deep Network
Eigen, D., Puhrsch, C., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1406.2283 · Cited by 3,442 · cited 1×
“Such techniques pose the problem as either inverse rendering [Barron and Malik 2015; Horn 1975] or supervised machine learning [Eigen et al. 2014; Hoiem et al. 2005; Liu et al. 2016; Saxena et al. 2009] and have seen significant progress, but this problem is highly underconstrained compared to…”
Method
Cited by
A Brief Survey on Semantic Segmentation with Deep Learning
Hao, S., Zhou, Y., & Guo, Y. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.11.118 · Cited by 596
Perceptual Quality Assessment of Smartphone Photography
Fang, Y., Zhu, H., Zeng, Y., Ma, K., & Wang, Z. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00373 · Cited by 375
NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
Mildenhall, B., Hedman, P., Martin-Brualla, R., Srinivasan, P. P., & Barron, J. T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01571 · Cited by 349
Self-citationConsistent video depth estimation
Luo, X., Huang, J.-B., Szeliski, R., Matzen, K., & Kopf, J. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392377 · Cited by 322
“Dense depth estimation facilitates a wide variety of visual effects such as synthetic depth-of-field [Wadhwa et al. 2018], novel view synthesis [Hedman et al.”
BackgroundSingle image portrait relighting
Sun, T., Barron, J. T., Tsai, Y.-T., Xu, Z., Yu, X., Fyffe, G., Rhemann, C., Busch, J., Debevec, P., & Ramamoorthi, R. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3323008 · Cited by 259
Self-citationDefocus Deblurring Using Dual-Pixel Data
Abuolaim, A., & Brown, M. S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58607-2_7 · Cited by 233
Recent advances in lensless imaging
Boominathan, V., Robinson, J. T., Waller, L., & Veeraraghavan, A. (2022) · Optica · doi:10.1364/optica.431361 · Cited by 218
Metadata
- Authors
- Wadhwa, N., Garg, R., Jacobs, D. E., Feldman, B. E., Kanazawa, N., Carroll, R., Movshovitz-Attias, Y., Barron, J. T., Pritch, Y., & Levoy, M.
- Venue
- ACM Transactions on Graphics
- Published
- 2018-07-30
- Volume
- 37
- Issue
- 4
- Pages
- 1-13
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W2808434111
- Cited by
- 173
- References
- 45
- FWCI
- 9.60
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.