https://github.com/xaviergrool/fgfusion
공식 코드FGFusion: Fine-Grained Lidar-Camera Fusion for 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.
FGFusion: Fine-Grained Lidar-Camera Fusion for 3D Object Detection
Behind the Curtain: Learning Occluded Shapes for 3D Object Detection
PE-YOLO: Pyramid Enhancement Network for Dark Object Detection
EagleVision: Object-level Attribute Multimodal LLM for Remote Sensing
RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition
PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
CAF-YOLO: A Robust Framework for Multi-Scale Lesion Detection in Biomedical Imagery
Learning Heavily-Degraded Prior for Underwater Object Detection
Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding
Generating Enhanced Negatives for Training Language-Based Object Detectors
Exploiting Unlabeled Data with Vision and Language Models for Object Detection
Accurate Single Stage Detector Using Recurrent Rolling Convolution
ScAR: Scaling Adversarial Robustness for LiDAR Object Detection
ScAR: Scaling Adversarial Robustness for LiDAR Object Detection
A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction
Self-Supervised Pretraining for RGB-D Salient Object Detection
Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline
Rethinking the Evaluation of Visible and Infrared Image Fusion
Fire and Smoke Detection with Burning Intensity Representation
DetCo: Unsupervised Contrastive Learning for Object Detection
PolarMask: Single Shot Instance Segmentation with Polar Representation
Towards Consistent Object Detection via LiDAR-Camera Synergy
From Simple to Professional: A Combinatorial Controllable Image Captioning Agent
Disentangled Pre-training for Human-Object Interaction Detection
Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.