daisily727

National Univ. of SingaporeSingapore

Pinned Repositories

3DVideos2Stereo
Code to extract stereo frame pairs from 3D videos, as used in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, arXiv:1907.01341"
Language:Python00
CAIN
Source code for AAAI 2020 paper "Channel Attention Is All You Need for Video Frame Interpolation"
Language:Python0 0 00
LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Language:Python00
Neural-Re-Rendering-of-Humans-from-a-Single-Image
Pytorch implementation of the paper, Neural re-rendering of humans from a single image.
Language:Jupyter Notebook00
X-Temporal
A general video understanding codebase from SenseTime X-Lab
Language:Python0 0 00

daisily727/3DVideos2Stereo
Code to extract stereo frame pairs from 3D videos, as used in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, arXiv:1907.01341"
Language:Python00
daisily727/CAIN
Source code for AAAI 2020 paper "Channel Attention Is All You Need for Video Frame Interpolation"
Language:Python0 0 00
daisily727/LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Language:Python00
daisily727/Neural-Re-Rendering-of-Humans-from-a-Single-Image
Pytorch implementation of the paper, Neural re-rendering of humans from a single image.
Language:Jupyter Notebook00
daisily727/X-Temporal
A general video understanding codebase from SenseTime X-Lab
Language:Python0 0 00