https://github.com/zyrant/cpdet3d
공식 코드Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection
SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection
FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network
Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning
PointCFormer: a Relation-based Progressive Feature Extraction Network for Point Cloud Completion
Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network
Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes
Blur Interpolation Transformer for Real-World Motion from Blur
Ultra-High-Definition Image Deblurring via Multi-scale Cubic-Mixer
MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restoration
Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
RGB-Event Fusion for Moving Object Detection in Autonomous Driving
Curricular Object Manipulation in LiDAR-based Object Detection
Co-Salient Object Detection with Co-Representation Purification
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks
Uncertainty-Aware AB3DMOT by Variational 3D Object Detection
Uncertainty-Aware AB3DMOT by Variational 3D Object Detection
Super accurate low latency object detection on a surveillance UAV
FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer
COVID-19 personal protective equipment detection using real-time deep learning methods
Faster-LTN: a neuro-symbolic, end-to-end object detection architecture
Pose2RGBD. Generating Depth and RGB images from absolute positions
Long-Term Temporally Consistent Unpaired Video Translation from Simulated Surgical 3D Data
An Energy-Aware Approach to Design Self-Adaptive AI-based Applications on the Edge
Structured Pruning and Quantization for Learned Image Compression
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.