https://github.com/surgical-vision/colmap-match-converter
공식 코드Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks
IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling
SUSTechGAN: Image Generation for Object Detection in Adverse Conditions of Autonomous Driving
EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy Network
SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and Tracking
Cascade-DETR: Delving into High-Quality Universal Object Detection
Camouflaged Object Detection with Feature Grafting and Distractor Aware
DSOD: Learning Deeply Supervised Object Detectors from Scratch
Improving Object Detection from Scratch via Gated Feature Reuse
Improving Object Detection from Scratch via Gated Feature Reuse
Designing A Sustainable Marine Debris Clean-up Framework without Human Labels
MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones
ConsistencyDet: A Few-step Denoising Framework for Object Detection Using the Consistency Model
Densely Deformable Efficient Salient Object Detection Network
LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond
GradAug: A New Regularization Method for Deep Neural Networks
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
Feature Aggregation and Propagation Network for Camouflaged Object Detection
Robust Video-Based Eye Tracking Using Recursive Estimation of Pupil Characteristics
FOVEA: Foveated Image Magnification for Autonomous Navigation
Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery
UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes
Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.