Xingtong Liu's repositories
EndoscopyDepthEstimation-Pytorch
Official Repo for the paper "Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning Methods" (TMI)
DenseDescriptorLearning-Pytorch
Official Repo for the paper "Extremely Dense Point Correspondences using a Learned Feature Descriptor" (CVPR 2020)
DenseReconstruction-Pytorch
Official Repo for the paper "Reconstructing Sinus Anatomy from Endoscopic Video -- Towards a Radiation-free Approach for Quantitative Longitudinal Assessment" (MICCAI 2020)
NeighborhoodNormalization-Pytorch
Official Repo for the paper "Neighborhood Normalization for Robust Geometric Feature Learning" (CVPR 2021)
GraduationProject-KukaNeedleAccurateInsertion
Graphic User Interface (GUI), drivers, and registration algorithms for accurate robot positioning (Kuka 6-joint industrial robot and Northern Digital Inc. optical tracking system)
Challenge2018
Part of the code for EndoVis 2018 robot scene segmentation challenge
Learning-to-See-Forces
Pytorch implementation of paper "Learning to See Forces: Surgical Force Prediction with RGB-Point Cloud Temporal Convolutional Networks" (MICCAI 2018 workshop)
Segment-and-Track-Anything
An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
stereo-transformer
Official Repo for Stereo Transformer: Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers.
Projective-Spatial-Transformers
Pytorch implementation of paper "Generalizing Spatial Transformers to Projective Geometry with Applications to 2D/3D Registration" (MICCAI 2020)
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
actions-setup-docker-compose
the GitHub Action setting up docker-compose command
git-recover
git-recover: recover deleted files in your repository
MinkowskiEngine
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
onnx2pytorch
Transform ONNX model to PyTorch representation
Pointnet2_PyTorch
PyTorch implementation of Pointnet2/Pointnet++
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
segmentation_models.pytorch
Segmentation models with pretrained backbones. PyTorch.