Minjun Kang's repositories
DualPixelFace
Facial Depth and Normal Estimation using Dual-Pixel Camera (ECCV 22)
SplattingAvatar
[CVPR2024] Official implementation of SplattingAvatar.
4K4D
4K4D: Real-Time 4D View Synthesis at 4K Resolution
D-SCRIPT
A structure-aware interpretable deep learning model for sequence-based prediction of protein-protein interactions
deformshape
Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects (ICCV2023)
diffusion-posterior-sampling
Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"
DiT
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
dpm-solver
Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)
ECON
ECON: Explicit Clothed humans Obtained from Normals
EditAnything
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc.
EFNet
Event-based Fusion for Motion Deblurring with Cross-modal Attention (ECCV'22 Oral) https://ahupujr.github.io/EFNet/
HOOD
Code for CVPR2023 paper "HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics"
MCG_diffusion
Official PyTorch implementation of the NeurIPS 2022 paper "Improving Diffusion Models for Inverse Problems using Manifold Constraints (https://arxiv.org/abs/2206.00941)"
Megatron-LM
Ongoing research training transformer models at scale
MeshDiffusion
Official implementation of "MeshDiffusion: Score-based Generative 3D Mesh Modeling" (ICLR 2023 Spotlight)
MinJunKang.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
Motion-X
Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"
nerfshop
NeRFshop: Interactive Editing of Neural Radiance Fields
particle-sfm
ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.
pypose
To connect classic robotics with modern learning methods seamlessly.
pytorch_geometric
Graph Neural Network Library for PyTorch
SHERF
SHERF learns a Generalizable Human NeRF to animate 3D humans from a single image.
sparsefusion
Official PyTorch implementation of SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction
TeCH
Official repo of "TeCH: Text-guided Reconstruction of Lifelike Clothed Humans"
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.