mlsanityData to 14 Oct 2026

AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving

arXiv 2309.06547 ↗First posted 12 Sep 2023cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 29 of its 55 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

29 of 55 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  3. 2018Datasheets for Datasetscited by 1,386
  4. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  5. 2022V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Drivingcited by 157
  6. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  7. 2022Vision-Centric BEV Perception: A Surveycited by 126
  8. 2023Delivering Arbitrary-Modal Semantic Segmentationcited by 117
  9. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  10. 2015Semantic Amodal Segmentationcited by 103
  11. 2018Searching for Efficient Multi-Scale Architectures for Dense Image Predictioncited by 96
  12. 2020ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentationcited by 96
17 more
  1. 2016Amodal Instance Segmentationcited by 63
  2. 2018Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentationcited by 62
  3. 2022Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditionscited by 48
  4. 2022Amodal Panoptic Segmentationcited by 38
  5. 2021Single Image Depth Estimation: An Overviewcited by 35
  6. 2022AISFormer: Amodal Instance Segmentation with Transformercited by 35
  7. 2023SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Imagescited by 35
  8. 2022SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Drivingcited by 32
  9. 20223D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attentioncited by 27
  10. 2015Amodal Completion and Size Constancy in Natural Scenescited by 21
  11. 2022Perceiving the Invisible: Proposal-Free Amodal Panoptic Segmentationcited by 21
  12. 2022Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping Through Continual Learningcited by 19
  13. 2022Learning Long-Horizon Robot Exploration Strategies for Multi-Object Search in Continuous Action Spacescited by 14
  14. 2022Neural Architecture Search for Dense Prediction Tasks in Computer Visioncited by 12
  15. 2022Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baselinecited by 12
  16. 2019Seeing Behind Things: Extending Semantic Segmentation to Occluded Regionscited by 11
  17. 2023Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilitiescited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 6; 2026: 3.

14 papers.

Sort:

By area:

  1. 2023Amodal Optical Flowcited by 8
  2. 2024Occlusion-Aware Seamless Segmentationcited by 7
  3. 2025Hyperspectral Adapter for Semantic Segmentation with Vision Foundation Modelscited by 7
  4. 2026ForecastOcc: Vision-based Semantic Occupancy Forecastingcited by 7
  5. 2025Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learningcited by 6
  6. 2024Amodal Depth Anything: Amodal Depth Estimation in the Wildcited by 5
  7. 2025Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentationcited by 4
  8. 2025Synth It Like KITTI: Synthetic Data Generation for Object Detection in Driving Scenarioscited by 3
  9. 2025Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURAcited by 3
  10. 2025RealDriveSim: A Realistic Multi-Modal Multi-Task Synthetic Dataset for Autonomous Drivingcited by 3
  11. 2024Foundation Models for Amodal Video Instance Segmentation in Automated Drivingcited by 1
  12. 2024WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model Researchcited by 0
2 more
  1. 2026Leveraging Vision-Based Point Cloud Map Priors for Camera-Based 3D Object Detection and Online Vectorized HD Mappingcited by 0
  2. 2026Perception Beyond the Visible: Incompleteness-Aware Scene Understanding for Robot Autonomycited by 0