2024/05/24 by Pan Liao, Feng Yang, Liao, Pan +5 · 1 citation
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Industrial Vision Systems and Defect Detection
paper · pdf · doi:10.48550/arxiv.2405.15176
openalex publication_date 2024/05/24 · openalex created_date 2024/05/28 · openalex updated_date 2026/07/28
Monocular 3D object detection has vast application potential across various fields. DETR-type models have shown remarkable performance in different areas, but there is still considerable room for improvement in monocular 3D detection, especially with the existing DETR-based method, MonoDETR. After addressing the query initialization issues in MonoDETR, we explored several performance enhancement strategies, such as incorporating a more efficient encoder and utilizing a more powerful depth estimator. Ultimately, we proposed MonoDETRNext, a model that comes in two variants based on the choice of depth estimator: MonoDETRNext-E, which prioritizes speed, and MonoDETRNext-A, which focuses on accuracy. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 3.52% improvement in the AP3D metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-E showed a 2.35% increase. Additionally, the computational efficiency of MonoDETRNext-E slightly exceeds that of its predecessor.