Interpolate and extrapolate video frames using cGAN
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
action_cls
analysis
figures
html
pred_flow
pred_flow_point
sr_code
x_code
.gitignore
README.md
label_all_img.txt
lena
split_train_test.py
t_imgs
testlist_gap1_full.txt
train_genlist_all_img.txt
train_genlist_all_img_1frame_reverse.txt
train_genlist_all_img_1frame_reverse_test.txt
train_genlist_all_img_1frame_reverse_train.txt
train_genlist_all_img_5frames.txt
train_genlist_all_img_5frames_test.txt
train_genlist_all_img_5frames_train.txt
train_genlist_all_img_firstlast.txt
train_genlist_all_img_test.txt
train_genlist_all_img_test_flow.txt
train_genlist_all_img_train.txt
train_genlist_all_img_train_flow.txt
trainlist_gap1_full.txt

README.md

Frame Prediction using cGAN

Interpolate and extrapolate video frames using cGAN

Authors: Hongyu Zhu, Xiaolong Wang and Siddha Ganju.

Network architecture

The GAN

### The generator

## Models and inputs
Models Generator (G) Discriminator (D)
Baseline 1st frame + noise future frame
FlowGAN 1st frame + flow (128x128) + noise flow (128x128) + future frame
FlowGAN-comp 1st frame + flow (128x128) + noise 1st frame + flow (128x128) + future frame
FlowGAN-sim 1st frame + flow (1x40) + noise flow (1x40) + future frame

Dataset and experiments

Frame prediction -- UCF101

The 6th frames

Every 5 frames recurrently

Action Recognition -- HMDB51

Static Image Editing -- MS COCO

GIFs with series of random flows