View-to-Label: Multi-View Consistency for Self-Supervised 3D Object Detection
원문 초록
For autonomous vehicles, driving safely is highly dependent on the capability to correctly perceive the environment in 3D space, hence the task of 3D object detection represents a fundamental aspect of perception. While 3D sensors deliver accurate metric perception, monocular approaches enjoy cost and availability advantages that are valuable in a wide range of applications. Unfortunately, training monocular methods requires a vast amount of annotated data. Interestingly, self-supervised approaches have recently been successfully applied to ease the training process and unlock access to widely available unlabelled data. While related research leverages different priors including LIDAR scans and stereo images, such priors again limit usability. Therefore, in this work, we propose a novel approach to self-supervise 3D object detection purely from RGB sequences alone, leveraging multi-view constraints and weak labels. Our experiments on KITTI 3D dataset demonstrate performance on par with state-of-the-art self-supervised methods using LIDAR scans or stereo images.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Frustum-PointPillars: A Multi-Stage Approach for 3D Object Detection using RGB Camera and LiDAR
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
Edge-Enabled Collaborative Object Detection for Real-Time Multi-Vehicle Perception
Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.