| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://richzhang.github.io/colorization/
x-github-request-id: F90E:3157C7:749E2D:82C709:6950D89E
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 07:13:36 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210071-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766906017.675393,VS0,VE200
vary: Accept-Encoding
x-fastly-request-id: f78eaf72af0f35a42515fb84d5b8470a2b8dc125
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sun, 04 Oct 2020 21:10:40 GMT
access-control-allow-origin: *
etag: W/"5f7a3a50-af01"
expires: Sun, 28 Dec 2025 07:23:37 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: CFF3:1387E:74CC6F:82F5C1:6950D8A0
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 07:13:37 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210071-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766906017.894157,VS0,VE204
vary: Accept-Encoding
x-fastly-request-id: 06506ff8616441b3fb55a58cedad8787de157aea
content-length: 9257
Colorful Image Colorization
Colorful Image Colorization
How to interpret the results
Welcome! Computer vision algorithms often work well on some images, but fail on others. Ours is like this too. We believe our work is a significant step forward in solving the colorization problem. However, there are still many hard cases, and this is by no means a solved problem. Some failure cases can be seen below and the figure here.
This is partly because our algorithm is trained on one million images from the Imagenet dataset, and will thus work well for these types of images, but not necessarily for others. We call this the "dataset bias" problem. We include colorizations of black and white photos of renowned photographers as an interesting "out-of-dataset" experiment and make no claims as to artistic improvements, although we do enjoy many of the results!
There has been some concurrent work on this subject as well. Specifically, see Larsson et al. and Iizuka et al. below.
Please enjoy our results, and if you're so inclined, try the model yourself!
Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We evaluate our algorithm using a "colorization Turing test," asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32% of the trials, significantly higher than previous methods. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. This approach results in state-of-the-art performance on several feature learning benchmarks.
We also provide an initial comparison against Cheng et al. 2015 here. We were unable to acquire code or results from the authors, so we simply ran our method on screenshots from the figures in the paper of Cheng et al. See Section 3 in the supplementary pdf for further discussion of the differences between our algorithm and that of Cheng et al.
Semantic interpretability of results
Click a category below to see our results on all test images in that category.
Deep Dream Visualization
|
|
|
|
|
|
|
|
|
|
|
|
|
 |
|
Welcome! Computer vision algorithms often work well on some images, but fail on others. Ours is like this too. We believe our work is a significant step forward in solving the colorization problem. However, there are still many hard cases, and this is by no means a solved problem. Some failure cases can be seen below and the figure here.
This is partly because our algorithm is trained on one million images from the Imagenet dataset, and will thus work well for these types of images, but not necessarily for others. We call this the "dataset bias" problem. We include colorizations of black and white photos of renowned photographers as an interesting "out-of-dataset" experiment and make no claims as to artistic improvements, although we do enjoy many of the results!
There has been some concurrent work on this subject as well. Specifically, see Larsson et al. and Iizuka et al. below.
Please enjoy our results, and if you're so inclined, try the model yourself!
Try the Interactive Demo
 |
| ECCV Talk 10/2016, also hosted on [VideoLectures] |
Try our code
 |
 |
Zhang, Isola, Efros. Colorful Image Colorization. In ECCV, 2016 (oral). (hosted on arXiv) |
Results on legacy black and white photos
 (hover for our results; click for full images) extention of Figure 15 from our paper |
 (hover for our results; click for full images) Figure 16 from our paper |
 (hover for our results; click for full images) Figure 17 from our paper |
Performance comparisons
 (hovering shows our results; click for additional examples) |
 (hovering shows our results; click for additional examples) |
We also provide an initial comparison against Cheng et al. 2015 here. We were unable to acquire code or results from the authors, so we simply ran our method on screenshots from the figures in the paper of Cheng et al. See Section 3 in the supplementary pdf for further discussion of the differences between our algorithm and that of Cheng et al.
Semantic interpretability of results
Deep Dream Visualization
 conv1_2 |
 conv2_1 |
 conv2_2 |
 conv3_1 |
 conv3_2 |
 conv3_3 |
 conv4_1 |
 conv4_2 |
 conv4_3 |
 conv5_1 |
 conv5_2 |
 conv5_3 |
 conv6_1 |
 conv6_2 |
 conv6_3 |
 conv7_1 |
 conv7_2 |
 conv7_3 |
User-Generated Examples |
Recent Related WorkGustav Larsson, Michael Maire, and Gregory Shakhnarovich. Learning Representations for Automatic Colorization. In ECCV 2016. [PDF][Website] Satoshi Iizuka, Edgar Simo-Serra, and Hiroshi Ishikawa. Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification. In SIGGRAPH, 2016. [PDF][Website] Ryan Dahl. Automatic Colorization. Jan 2016. [Website] Aditya Deshpande, Jason Rock and David Forsyth. Learning Large-Scale Automatic Image Colorization. In ICCV, Dec 2015. [PDF][Website] Zezhou Cheng, Qingxiong Yang, and Bin Sheng. Deep Colorization. In ICCV, Dec 2015. [PDF] |
Acknowledgements |