paper-with-me

홈 › Papers

AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving

2023-09-12 · Ahmed Rida Sekkat, Rohit Mohan, Oliver Sawade, Elmar Matthes, Abhinav Valada

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.

📄 PDF Abstract BibTeX arXiv:2309.06547

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingBenchmarkingDepth EstimationScene Understanding

Similar Papers 제목 키워드 기반

Amodal Optical Flow

2023-11-13 · Maximilian Luz, Rohit Mohan, Ahmed Rida Sekkat, Oliver Sawade 외

Optical flow estimation is very challenging in situations with transparent or occluded objects. In this work, we address these challenges at the task level by introducing Amodal Optical Flow, which integrates optical flo…

DecoderOptical Flow EstimationPanoptic Tracking

Amodal Intra-class Instance Segmentation: Synthetic Datasets and Benchmark

2023-03-12 · Jiayang Ao, Qiuhong Ke, Krista A. Ehinger

Images of realistic scenes often contain intra-class objects that are heavily occluded from each other, making the amodal perception task that requires parsing the occluded parts of the objects challenging. Although impo…

Amodal Instance SegmentationInstance SegmentationRobotic GraspingSemantic Segmentation

Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baseline

2022-06-01 · Jasmin Breitenstein, Tim Fingscheidt

Amodal perception terms the ability of humans to imagine the entire shapes of occluded objects. This gives humans an advantage to keep track of everything that is going on, especially in crowded situations. Typical perce…

SegmentationSemantic Segmentation

TAO-Amodal: A Benchmark for Tracking Any Object Amodally

2023-12-19 · Cheng-Yen Hsieh, Kaihua Chen, Achal Dave, Tarasha Khurana 외

Amodal perception, the ability to comprehend complete object structures from partial visibility, is a fundamental skill, even for infants. Its significance extends to applications like autonomous driving, where a clear u…

Amodal TrackingAutonomous DrivingBenchmarkingData Augmentation+1

Segment Anything, Even Occluded

2025-03-08 · CVPR 2025 1 · Wei-En Tai, Yu-Lin Shih, Cheng Sun, Yu-Chiang Frank Wang 외

Amodal instance segmentation, which aims to detect and segment both visible and invisible parts of objects in images, plays a crucial role in various applications including autonomous driving, robotic manipulation, and s…

Amodal Instance SegmentationAutonomous DrivingDecoderInstance Segmentation+3