VDIGPKU

M2Det

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

CBNet_caffe

Composite Backbone Network (AAAI20)

CBNetV2

[TIP 2022] CBNetV2: A Composite Backbone Network Architecture for Object Detection

GALA3D

[ICML 2024] GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting

CFENet

Comprehensive Feature Enhancement Module for Single-Shot Object Detector

DADA

[ECCV 2020] DADA: Differentiable Automatic Data Augmentation

DrivingGaussian

[CVPR 2024] DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

DynamicDet

[CVPR 2023] DynamicDet: A Unified Dynamic Architecture for Object Detection

CBNet_pytorch

CBNet implementation based on mmdetection (AAAI 2020)

T-SEA

[CVPR 2023] T-SEA: Transfer-based Self-Ensemble Attack on Object Detection

CMUA-Watermark

[AAAI 2022] CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes

RCBEVDet

[CVPR 2024] RCBEVDet: Radar-camera Fusion in Bird’s Eye View for 3D Object Detection

OPANAS

[CVPR 2021]OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

RPAttack

(ICME2021) RPATTACK: REFINED PATCH ATTACK ON GENERAL OBJECT DETECTORS

QGCN

Learning a Single Model With a Wide Range of Quality Factors for JPEG Image Artifacts Removal (TIP 2020)

BEV-MAE

[AAAI 2024] BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

HENet

HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras

STR_TPSearch

FlowNAS

[IJCV 2023] FlowNAS: Neural Architecture Search for Optical Flow Estimation

IterNet

GSTO

official implementation of paper: GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling

ContinualContrastiveLearning

[ICME 2022] Continual Contrastive Learning for Image Classification

MixTConv

SAMPLING

[ICCV 2023] SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image

SReN_MM

A-quadrilateral-scene-text-detector

FORMULA

[WACV 2023] Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers

BEVFusion

Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"

VDIGPKU.github.io