MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It outperforms the previous best method by +3.0 NDS and +1.6 mAP on a challenging long-range perception benchmark, introducing a novel sparse fusion approach.
Who it is for
- Autonomous driving researchers
- Perception engineers
- Computer vision scientists
- Sensor fusion specialists
Use cases
- Long-range 3D object detection for autonomous vehicles
- Robust perception in adverse weather (radar benefits)
- Improving detection with sparse sensor data
- Benchmarking on TruckScenes dataset
Strengths
- Outperforms prior state-of-the-art by significant margins (+3.0 NDS, +1.6 mAP)
- Sparse BEV features reduce computational overhead
- Gaussian primitives enhance representation of radar data
- Published at ECCV 2026
Considerations
- Code and pretrained models not yet released
- Evaluation limited to TruckScenes dataset only
- No comparison with camera-only or radar-only baselines shown in README
README quick start
Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Driving
ECCV 2026
Geonho Bang, Geunju Baek, Dongyoung Lee, Wonjun Jeong, Jun Won Choi Seoul National University
🌐 Project page: https://geonhobang.github.io/horizon3d-project-page/
⏳ Code will be released soon.
We propose Horizon3D, a sparse radar-camera fusion framework for long-range 3D object detection that combines Gaussian primitives with sparse BEV features (KGGI → OCSF → DPTF). On TruckScenes it outperforms the previous best method by +3.0 NDS and +1.6 mAP.
The code and pretrained models will be made available here upon publication.
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.