SOTAVerified

Multispectral Object Detection

Only using RGB cameras for automatic outdoor scene analysis is challenging when, for example, facing insufficient illumination or adverse weather. To improve the recognition reliability, multispectral systems add additional cameras (e.g. infra-red) and perform object detection from multispectral data. Although multispectral scene analysis with deep learning has be shown to have a great potential, there are still many open research questions and it has not been widely deployed in industrial contexts.

Papers

Showing 110 of 39 papers

TitleStatusHype
YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection FrameworkCode4
Multispectral Detection Transformer with Infrared-Centric Sensor FusionCode0
Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarks0
CAFF-DINO: Multi-spectral object detection transformers with cross-attention features fusion0
Surveying You Only Look Once (YOLO) Multispectral Object Detection Advancements, Applications And Challenges0
When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark DatasetCode2
RGB-T Object Detection via Group Shuffled Multi-receptive Attention and Multi-modal Supervision0
Rethinking Early-Fusion Strategies for Improved Multispectral Object DetectionCode1
MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object DetectionCode1
UniRGB-IR: A Unified Framework for RGB-Infrared Semantic Tasks via Adapter TuningCode2
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MMPedestronmAP5086.4Unverified
2RGB-X Scene Adaptive CBAMmAP5086.16Unverified
3CAFF-DINOmAP5085.5Unverified
4RSDetmAP5083.9Unverified
5CMXmAP5082.2Unverified
6UniRGB-IRmAP5081.4Unverified
7MiPamAP5081.3Unverified
8CSSAmAP5079.2Unverified
9CFTmAP5077.7Unverified
10ProbEnmAP5075.5Unverified