3D Reconstruction with Spatial Memory

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

Sources used to compare the MKF orientation estimation approaches.

attitude estimator with gyro bias correction

A C++ implementation of a nonlinear 3D IMU fusion algorithm

Fisheye-Calib-Adapter: An Easy Tool for Fisheye Camera Model Conversion

Image2Image Translation Research

Open Neural Network Compiler

CUDA Templates for Linear Algebra Subroutines

This is an official repository of End-to-end Lane Shape Prediction with Transformers.

Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…

official code for paper "MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles"

[CVPR 2020--Oral] CycleISP: Real Image Restoration via Improved Data Synthesis

Pytorch implementation of Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

A collection of extensions for Vitis and Intel FPGA OpenCL to improve developer quality of life.

Scalable systolic array-based matrix-matrix multiplication implemented in Vivado HLS for Xilinx FPGAs.

DerainZoo for collecting deraining methods, datasets, and codes.

A collection of deep learning based methods for HDR image synthesis

Code repository for our paper Chongyi Li, Chunle Guo, Wenqi Ren, Runmin Cong, Junhui Hou, Sam Kwong, Dacheng Tao , "An Underwater Image Enhancement Benchmark Dataset and Beyond" IEEE TIP 2019.

Semantic information can help CNNs to get better illuminant estimation -- a proof of concept

XJTU-Tripler is based on HiPU100, an FPGA-friendly DNN accelerator, developed by CAG, Institute of AI & Robotics, XJTU.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Python implementation of the video stabilizing algorithm used in YouTube

Visual Object Tracking algorithms. Hold on! There is a lot to come

This work proposes a feature refined end-to-end tracking framework with a balanced performance using a high-level feature refine tracking framework. The feature refine module enhances the target fe…

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".