Final Projects

Roth Yin | rothyin@berkeley.edu

A Neural Algorithm of Artistic Style

We follow the paper. We use VGG19 Net, backpropping on an image (or white noise) so that it converges to the desired content and style image with respective weights.

Visual Results

style image	generated output

Experiment with different weight of content and style, and layers of net

	10^5	10^4	10^3	10^2
1 layer
2 layer
2 layer
3 layer
4 layer

Poor Man's Augmented Reality

We first use plt.ginput to get the camera coordinates of the box.
We then use cv2.TrackerMedianFlow_create() to estimate the camera coordinates for all the other frames.
We then find camera projection with least square for each frame.

Bells & Whistles (Extra Point)

We use pyrender to render the object. We set pyrender.constants.RenderFlags.RGBA to get RGBA images so that it can be blended with the video frames.
In addition to cv2.calibrateCamera, we also need cv2.Rodrigues to facilitate us to get the Rt matrix.
Afterwards we traverse through the frames and calculate the new Rt matrix for every frame to position and rotate the mesh object.