diff options
| author | Cameron <cysmith1010@gmail.com> | 2016-11-07 22:02:24 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2016-11-07 22:02:24 -0700 |
| commit | 8539b2fe348d0433460cbee5bbb91e57810b2c64 (patch) | |
| tree | 8dda3e974db85d35c5bdbe775e81076fb310178d | |
| parent | 10f7478ecf387e767674f7b568e761a67554819e (diff) | |
Update README.md
| -rw-r--r-- | README.md | 4 |
1 files changed, 3 insertions, 1 deletions
@@ -157,7 +157,9 @@ Animations can be rendered by applying the algorithm to each source frame. For <br> <img src="examples/video/weights.gif"> <img src="examples/video/output.gif"> -</p> +</p> +*Top row (left to right)*: source frames, ground truth optical flow +*Bottom row (left to right)*: disoccluded regions and motion boundaries, stylized frames ### Gradient Descent Initialization The initialization of the gradient descent is controlled using `--init_img_type` for single images and `--init_frame_type` or `--first_frame_type` for video frames. White noise allows an arbitrary number of distinct images to be generated. Whereas, initializing with a fixed image always converges to the same output. |