From e753eaa0d43e15d4247512cf5be37705490dfc4c Mon Sep 17 00:00:00 2001 From: Amir Hassan Date: Sun, 4 Dec 2022 12:17:23 +0100 Subject: [PATCH 1/3] Update README.md --- README.md | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index fa37fdc06..48486d2c1 100644 --- a/README.md +++ b/README.md @@ -5,6 +5,7 @@ The goal of the demos is to show how to use OpenCL interop in conjunction with O * The author of the example video (which is also used for two of the demo videos in this README) is **(c) copyright Blender Foundation | www.bigbuckbunny.org**. * The author of the video used for pedestrian detection is **GNI Dance Company** ([Original video](https://www.youtube.com/watch?v=yg6LZtNeO_8)) +* The author of the video used for face beautification is **Nina Ubhi** ([Original video](https://www.youtube.com/watch?v=gkkmHizG2As&t=2s)) * The right holders of the video used for the optical flow visualization are **https://www.bbtv.com**. I tried to contact them several times to get an opinion on my fair-use for educational purpose. ([Original video](https://www.youtube.com/watch?v=ItGwXRCcisA)) # Requirements @@ -12,7 +13,7 @@ The goal of the demos is to show how to use OpenCL interop in conjunction with O * Support for cl_khr_gl_sharing and cl_intel_va_api_media_sharing OpenCL extensions. * If you are on a recent Intel Platform (Gen8 - Gen12) you **need to install** an [**alternative compute-runtime**](https://github.com/kallaballa/compute-runtime) -There are currently six demos (**the preview videos are scaled down and compressed**): +There are currently seven demos (**the preview videos are scaled down and compressed**): ## tetra-demo Renders a rainbow tetrahedron on blue background using OpenGL, applies a glow effect using OpenCV (OpenCL) and encodes on the GPU (VAAPI). @@ -44,6 +45,15 @@ Note: Detection rate is not very impressive and depends highly on the video. https://user-images.githubusercontent.com/287266/204570888-9bf48c6e-3422-4fce-94e4-27a98db76dea.mp4 +## beauty-demo +Face beautification using face landmark detection (OpenCV/OpenCL), nanovg (OpenGL) for drawing masks and multi-band (OpenCV/OpenCL) blending to put it all together. Note: There are sometimes little glitches because face landmark detection is not very accurate and has rather few points. + + + +https://user-images.githubusercontent.com/287266/205487316-98f14324-7885-4647-b913-87fdc8aa3347.mp4 + + + # Instructions You need to build my 4.x branch of OpenCV. @@ -106,4 +116,10 @@ src/optflow/optflow-demo bunny.webm src/pedestrian/pedestrian-demo bunny.webm ``` +## Run the beauty-demo: + +```bash +src/beauty/beauty-demo bunny.webm +``` + From 0e75950d480b71e7ea6a49ea6874a33b86049673 Mon Sep 17 00:00:00 2001 From: Amir Hassan Date: Sun, 4 Dec 2022 12:38:00 +0100 Subject: [PATCH 2/3] Update README.md --- README.md | 6 ------ 1 file changed, 6 deletions(-) diff --git a/README.md b/README.md index 48486d2c1..63b0d0b69 100644 --- a/README.md +++ b/README.md @@ -48,12 +48,6 @@ https://user-images.githubusercontent.com/287266/204570888-9bf48c6e-3422-4fce-94 ## beauty-demo Face beautification using face landmark detection (OpenCV/OpenCL), nanovg (OpenGL) for drawing masks and multi-band (OpenCV/OpenCL) blending to put it all together. Note: There are sometimes little glitches because face landmark detection is not very accurate and has rather few points. - - -https://user-images.githubusercontent.com/287266/205487316-98f14324-7885-4647-b913-87fdc8aa3347.mp4 - - - # Instructions You need to build my 4.x branch of OpenCV. From efc34310abdb6090c35ebf47caaa455c3df02a95 Mon Sep 17 00:00:00 2001 From: Amir Hassan Date: Sun, 4 Dec 2022 12:38:16 +0100 Subject: [PATCH 3/3] Update README.md --- README.md | 1 - 1 file changed, 1 deletion(-) diff --git a/README.md b/README.md index 63b0d0b69..6c6c7883a 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,6 @@ The goal of the demos is to show how to use OpenCL interop in conjunction with O * The author of the example video (which is also used for two of the demo videos in this README) is **(c) copyright Blender Foundation | www.bigbuckbunny.org**. * The author of the video used for pedestrian detection is **GNI Dance Company** ([Original video](https://www.youtube.com/watch?v=yg6LZtNeO_8)) -* The author of the video used for face beautification is **Nina Ubhi** ([Original video](https://www.youtube.com/watch?v=gkkmHizG2As&t=2s)) * The right holders of the video used for the optical flow visualization are **https://www.bbtv.com**. I tried to contact them several times to get an opinion on my fair-use for educational purpose. ([Original video](https://www.youtube.com/watch?v=ItGwXRCcisA)) # Requirements