You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
PopSift is an open-source implementation of the SIFT algorithm in CUDA.
@@ -33,7 +33,7 @@ Optionally, for the provided applications:
33
33
34
34
To build the library, you can run:
35
35
36
-
```
36
+
```shell
37
37
mkdir build &&cd build
38
38
cmake ..
39
39
make
@@ -101,7 +101,7 @@ PopSift can be configured at runtime to use constants that affect its behaviours
101
101
In particular, users can choose to generate results very similar to VLFeat or results that are closer (but not as close) to the SIFT implementation of the OpenCV extras.
102
102
We acknowledge that there is at least one SIFT implementation that is vastly faster, but it makes considerable sacrifices in terms of accuracy and compatibility.
103
103
104
-
## Continuous integration:
104
+
## Continuous integration
105
105
106
106
* master branch (Linux and Windows).
107
107
@@ -113,29 +113,28 @@ PopSift is licensed under [MPL v2 license](COPYING.md).
113
113
SIFT was patented in the United States from 1999-03-08 to 2020-03-28. See the [patent link](https://patents.google.com/patent/US6711293B1/en) for more information.
114
114
PopSift license only concerns the PopSift source code and does not release users of this code from any requirements that may arise from patents.
115
115
116
-
117
116
## Cite Us
118
117
119
118
If you use PopSift for your publication, please cite us as:
119
+
120
120
```bibtex
121
121
@inproceedings{Griwodz2018Popsift,
122
-
author = {Griwodz, Carsten and Calvet, Lilian and Halvorsen, P{\aa}l},
123
-
title = {Popsift: A Faithful SIFT Implementation for Real-time Applications},
124
-
booktitle = {Proceedings of the 9th {ACM} Multimedia Systems Conference},
125
-
series = {MMSys '18},
126
-
year = {2018},
127
-
isbn = {978-1-4503-5192-8},
128
-
location = {Amsterdam, Netherlands},
129
-
pages = {415--420},
130
-
numpages = {6},
131
-
doi = {10.1145/3204949.3208136},
132
-
acmid = {3208136},
133
-
publisher = {ACM},
134
-
address = {New York, NY, USA},
122
+
author = {Griwodz, Carsten and Calvet, Lilian and Halvorsen, P{\aa}l},
123
+
title = {Popsift: A Faithful SIFT Implementation for Real-time Applications},
124
+
booktitle = {Proceedings of the 9th {ACM} Multimedia Systems Conference},
125
+
series = {MMSys '18},
126
+
year = {2018},
127
+
isbn = {978-1-4503-5192-8},
128
+
location = {Amsterdam, Netherlands},
129
+
pages = {415--420},
130
+
numpages = {6},
131
+
doi = {10.1145/3204949.3208136},
132
+
acmid = {3208136},
133
+
publisher = {ACM},
134
+
address = {New York, NY, USA},
135
135
}
136
136
```
137
137
138
-
139
138
## Acknowledgements
140
139
141
140
PopSift was developed within the project [POPART](https://alicevision.org/popart), which has been funded by the [European Commission in the Horizon 2020](https://cordis.europa.eu/project/id/644874) framework.
0 commit comments