ziming-liu

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

FastSAM

Fast Segment Anything

consistency_models

Official repo for consistency models.

gdown

Google Drive Public File Downloader when Curl/Wget Fails

sru

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

pypose

A library for differentiable robotics.

MaskDINO

[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"

Campus2024

2024届互联网校招信息汇总

mmflow

OpenMMLab optical flow toolbox and benchmark

RAFT-Stereo

Context-Cluster

[ICLR 2023 Oral] Image as Set of Points

IGEV

[CVPR 2023] Iterative Geometry Encoding Volume for Stereo Matching and Multi-View Stereo

cascade-stereo

cascade-stereo

ACVNet

[CVPR 2022] ACVNet: Attention Concatenation Volume for Accurate and Efficient Stereo Matching

NVDS

The official repository of the ICCV2023 paper "Neural Video Depth Stabilizer" (NVDS).

adahessian

ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning

CREStereo-Pytorch

Non-official Pytorch implementation of the CREStereo(CVPR 2022 Oral).

optimizers

For optimization algorithm research and development.

Deep-SLAM

a list of papers, code, and other resources focus on deep learning SLAM system

UnDepthflow

HITNET-Stereo-Depth-estimation

Python scripts for performing stereo depth estimation using the HITNET Tensorflow model.

monodepth_benchmark

Code for "Deconstructing Monocular Depth Reconstruction: The Design Decisions that Matter" (https://arxiv.org/abs/2208.01489)

FastSam_Awsome_TensorRT

awesome-deep-visual-odometry

A repository to keep track of Deep Learning based methods for visual odometry (pull requests are always welcome)

DOPlearning

Code for T-ITS paper "Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry" and for ICRA paper "Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks".

cuda-gridsample-grad2

Cuda implementation for gridsample with second derivative support

vid2depth

This is the separated vid2depth from tensorflow/models, some lines are commented or changed for successful inference.

Lasagne

SGN

An efficient and easy-to-use Theano implementation of the stochastic Gauss-Newton method for training deep neural networks.