mlsanityData to 7 Oct 2026

MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders

arXiv 2405.07696 ↗First posted 13 May 2024cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Monocular 3D object detection aims for precise 3D localization and identification of objects from a single-view image. Despite its recent progress, it often struggles while handling pervasive object occlusions that tend to complicate and degrade the prediction of object dimensions, depths, and orientations. We design MonoMAE, a monocular 3D detector inspired by Masked Autoencoders that addresses the object occlusion issue by masking and reconstructing objects in the feature space. MonoMAE consists of two novel designs. The first is depth-aware masking that selectively masks certain parts of non-occluded object queries in the feature space for simulating occluded object queries for network training. It masks non-occluded object queries by balancing the masked and preserved query portions adaptively according to the depth information. The second is lightweight query completion that works with the depth-aware masking to learn to reconstruct and complete the masked object queries. With the proposed object occlusion and completion, MonoMAE learns enriched 3D representations that achieve superior monocular 3D detection performance qualitatively and quantitatively for both occluded and non-occluded objects. Additionally, MonoMAE learns generalizable representations that can work well in new domains.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 59 of its 74 references that are in the map. First posted on arXiv 13 May 2024.

Builds on

59 of 74 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2015Fast R-CNNcited by 2,930
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  9. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  10. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  11. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  12. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
38 more
  1. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  2. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  3. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  4. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  5. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  6. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  7. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  8. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  9. 2019Disentangling Monocular 3D Object Detectioncited by 215
  10. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 202
  11. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  12. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  13. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  14. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  15. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  16. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  17. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  18. 2020Kinematic 3D Object Detection in Monocular Videocited by 116
  19. 2020Rethinking Pseudo-LiDAR Representationcited by 109
  20. 2022MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformercited by 108
  21. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  22. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  23. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 83
  24. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  25. 2018Joint Monocular 3D Vehicle Detection and Trackingcited by 77
  26. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  27. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 66
  28. 2016Amodal Instance Segmentationcited by 63
  29. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  30. 2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 57
  31. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  32. 2023PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detectioncited by 53
  33. 2022DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detectioncited by 48
  34. 2022DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detectioncited by 39
  35. 2024LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptorscited by 39
  36. 2024MonoCD: Monocular 3D Object Detection with Complementary Depthscited by 38
  37. 2019Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priorscited by 37
  38. 2023Learning Occupancy for Monocular 3D Object Detectioncited by 35

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 10; 2026: 3.

15 papers.

Sort:

By area:

  1. 2025Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detectioncited by 8
  2. 2025Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURAcited by 3
  3. 2025MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detectioncited by 2
  4. 2025IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detectioncited by 2
  5. 2026Towards Intrinsic-Aware Monocular 3D Object Detectioncited by 2
  6. 2025LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detectioncited by 1
  7. 2024Efficient Strategy Learning by Decoupling Searching and Pathfinding for Object Navigationcited by 0
  8. 2024Revisiting Monocular 3D Object Detection with Depth Thickness Fieldcited by 0
  9. 2025BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecastingcited by 0
  10. 2025MonoVQD: Monocular 3D Object Detection with Variational Query Denoising and Self-Distillationcited by 0
  11. 2025Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detectioncited by 0
  12. 2025LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Spacecited by 0
3 more
  1. 2025Auto-Vocabulary 3D Object Detectioncited by 0
  2. 2026MonoPRIO: Adaptive Prior Conditioning for Unified Monocular 3D Object Detectioncited by 0
  3. 2026RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detectioncited by 0