AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving
원문 초록
Unlike humans, who can effortlessly estimate the entirety of objects even when partially occluded, modern computer vision algorithms still find this aspect extremely challenging. Leveraging this amodal perception for autonomous driving remains largely untapped due to the lack of suitable datasets. The curation of these datasets is primarily hindered by significant annotation costs and mitigating annotator subjectivity in accurately labeling occluded regions. To address these limitations, we introduce AmodalSynthDrive, a synthetic multi-task multi-modal amodal perception dataset. The dataset provides multi-view camera images, 3D bounding boxes, LiDAR data, and odometry for 150 driving sequences with over 1M object annotations in diverse traffic, weather, and lighting conditions. AmodalSynthDrive supports multiple amodal scene understanding tasks including the introduced amodal depth estimation for enhanced spatial understanding. We evaluate several baselines for each of these tasks to illustrate the challenges and set up public benchmarking servers. The dataset is available at http://amodalsynthdrive.cs.uni-freiburg.de.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation
Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation
Point Cloud Compression and Objective Quality Assessment: A Survey
Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios
Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systems
Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment
토론
이 논문과 연결된 포럼 글이 아직 없습니다.