Visual point cloud forecasting enables scalable autonomous driving
In contrast to extensive studies on general vision pre-training for scalable visual
autonomous driving remains seldom explored. Visual autonomous driving applications …
autonomous driving remains seldom explored. Visual autonomous driving applications …
Driveworld: 4d pre-trained scene understanding via world models for autonomous driving
Vision-centric autonomous driving has recently raised wide attention due to its lower cost.
Pre-training is essential for extracting a universal representation. However current vision …
Pre-training is essential for extracting a universal representation. However current vision …
Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities
The rise of large foundation models, trained on extensive datasets, is revolutionizing the
field of AI. Models such as SAM, DALL-E2, and GPT-4 showcase their adaptability by …
field of AI. Models such as SAM, DALL-E2, and GPT-4 showcase their adaptability by …
Occfiner: Offboard occupancy refinement with hybrid propagation
Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC),
presents a significant challenge in computer vision. Previous methods, confined to onboard …
presents a significant challenge in computer vision. Previous methods, confined to onboard …
Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection
Popular representation learning methods encourage feature invariance under
transformations applied at the input. However, in 3D perception tasks like object localization …
transformations applied at the input. However, in 3D perception tasks like object localization …