Timeline for How can I determine whether a video's frame is realistic (was recorded by a camera) or contains computer-generated graphics?
Current License: CC BY-SA 4.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 25, 2020 at 20:36 | vote | accept | Mary | ||
| Oct 25, 2020 at 9:57 | history | edited | nbro | CC BY-SA 4.0 |
added 2 characters in body; edited title
|
| Oct 24, 2020 at 19:22 | review | Close votes | |||
| Oct 27, 2020 at 1:39 | |||||
| Oct 24, 2020 at 12:33 | comment | added | Aray Karjauv | I posted my answer. Feel free to ask me if anything is unclear. If the answer is helpful, don't forget to accept it. | |
| Oct 23, 2020 at 21:36 | answer | added | Aray Karjauv | timeline score: 2 | |
| Oct 23, 2020 at 19:15 | comment | added | Mary | Umm I'm not yet much into architecting deep layers. If you could post a sample in python using Keras, it would be great. | |
| Oct 23, 2020 at 14:25 | comment | added | Aray Karjauv | It depends. If you have a series of images (i.e. a video), you can use LSTM to improve stability. But I would suggest starting simple. To make it lightweight, you can also downscale the images to smaller resolution and make them b&w. You can also use maxpooling layers/strides in your CNN | |
| Oct 23, 2020 at 14:10 | comment | added | Mary | Should it be CNN only, or LSTM with multiple frames?! I need it to be lightweight. | |
| Oct 23, 2020 at 10:34 | comment | added | Aray Karjauv | Since neural networks are very good at finding patterns, you can try to just train a neural network (e.g. CNN) on you examples given the labels whether it is real or CGI. If you want then to understand what your NN has learned, you can visualize its layers | |
| Oct 23, 2020 at 6:56 | comment | added | Hiren Namera | Why not you try ELA(Error Level Analysis). Using ELA you can identifyedited scenes and non edited scenes. | |
| Oct 23, 2020 at 0:24 | history | asked | Mary | CC BY-SA 4.0 |