Gaurav's repositories
YOLOE
PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL.
Object-Localization-Network
Therefore, Author propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlap with any ground-truth object (e.g., centerness and IoU).
Oriented-Object-Detection-in-Aerial-Images
Oriented object detection in aerial images is a challenging task as the objects in aerial images are displayed in arbitrary directions and are usually densely packed. Current oriented object detection methods mainly rely on twostage anchor-based detectors
PINTO_model_zoo
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
PyTorch-Quantization
Quantization is the process of mapping continuous infinite values to a smaller set of discrete finite values. In the context of simulation and embedded computing, it is about approximating real-world values with a digital representation that introduces limits on the precision and range of a value
VideoDemoireing_Model
VideoDemoireing_Model
2StageAlign
The official codes of our CVPR2022 paper: A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift
AISP
AI Image SIgnal Processing - AIM 2022 Reversed ISP Challenge @ ECCV, Model-Based Image Signal Processors via Learnable Dictionaries (AAAI 22)
Awesome-Transformer-Attention
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
CenterNet2
Two-stage CenterNet
Content-Aware-Dynamic-Quantization-for-Image-Super-Resolution
The overview of the proposed quantization framework CADyQ for SR network, which we illustrate with a residual block based backbone. For each given patch and each layer, our CADyQ module introduces a light-weight bit selector that dynamically selects the bit-width and its corresponding quantization function among the candidate quantization functions with distinct bit-widths.
Deep-FlexISP
This is the official implementation of "Deep-FlexISP: A Three-Stage Framework for Night Photography Rendering"
ESPCN
Approaches based on the convolutional neural network like SRCNN, FSRCNN, and VDSR have some drawbacks. Firstly, CNN approaches need to use interpolation methods to upsample the LR image, such as bicubic interpolation. Secondly, it increases the resolution before or at the first layer of the network
HDR-Plenoxels
[ECCV'22] Official PyTorch Implementation of "HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields"
Low-Level-Vision-Paper-Record
记录近期的 1) 图像/视频的超分增强等low level vision任务; 2) 图像生成 等任务相关论文, 主要为18年以后的DL based方法.
MuLUT
[ECCV 2022]MuLUT: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution
Retinex
Python implementation of multi scale retinex with color restoration
SSD_Pytorch
SSD is an anchor-bassed version for Object detection
The-Art-of-Linear-Algebra
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
VideoDemoireing
(CVPR 2022) Video Demoireing with Relation-Based Temporal Consistency
WaveNet
[PG 2023] WaveNet: Wave-Aware Image Enhancement
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite