-
KAIST, Visual Media Lab.
- KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
- http://vml.kaist.ac.kr
Stars
Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
MATLAB implementation of the paper "Robust Uncertainty-Aware Multiview Triangulation"
Google Research
Inference Code for DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse point (ECCV 2020)s
Code for "Layered Neural Rendering for Retiming People in Video."
[PAMI] End-to-end Full Projector Compensation
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
A simple method to perform semi-supervised learning with limited data.
Code release for ICCV 2019 Oral, "Linearized Multi-Sampling for Differentiable Image Transformation"
[ICCV'19] CompenNet++: End-to-end Full Projector Compensation
[TASE & ISMAR'18] A Fast and Flexible Projector-Camera Calibration System
A dark style sheet for QtWidgets application
UnityProjectionMapping source(for camera distortion)
Open3D: A Modern Library for 3D Data Processing
video stabilization with CNN https://ieeexplore.ieee.org/document/8554287
Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Pytorch implementation of "Video Generation from Single Semantic Label Map", CVPR 2019
StyleGAN - Official TensorFlow Implementation
PyTorch Tutorial for Deep Learning Researchers
Transformation-Grounded Image Generation Network for Novel 3D View Synthesis
PyTorch implementation of Super SloMo by Jiang et al.
Taskonomy: Disentangling Task Transfer Learning [Best Paper, CVPR2018]