# OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection

arXiv: https://arxiv.org/abs/2211.01142 · HTML: https://mlsanity.com/paper/2211.01142/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 54 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 30 of 46)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [Disentangling Monocular 3D Object Detection](https://mlsanity.com/paper/1905.12365/) (2019)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [CenterMask : Real-Time Anchor-Free Instance Segmentation](https://mlsanity.com/paper/1911.06667/) (2019)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://mlsanity.com/paper/2002.12212/) (2020)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships](https://mlsanity.com/paper/2003.00504/) (2020)
- [CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection](https://mlsanity.com/paper/2009.00784/) (2020)
- [Delving into Localization Errors for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16237/) (2021)
- [Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving](https://mlsanity.com/paper/1903.11444/) (2019)
- [ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape](https://mlsanity.com/paper/1812.02781/) (2018)
- [Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud](https://mlsanity.com/paper/1903.09847/) (2019)
- [Rethinking Pseudo-LiDAR Representation](https://mlsanity.com/paper/2008.04582/) (2020)
- [MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer](https://mlsanity.com/paper/2203.10981/) (2022)
- [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://mlsanity.com/paper/1903.10955/) (2019)

## Built on by (most cited first, 24 of 24)

- [SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation](https://mlsanity.com/paper/2311.11125/) (2023)
- [On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks](https://mlsanity.com/paper/2303.14840/) (2023)
- [MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors](https://mlsanity.com/paper/2410.19590/) (2024)
- [DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field](https://mlsanity.com/paper/2308.08231/) (2023)
- [HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation](https://mlsanity.com/paper/2311.12588/) (2023)
- [MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders](https://mlsanity.com/paper/2405.07696/) (2024)
- [IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction](https://mlsanity.com/paper/2303.00575/) (2023)
- [MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision](https://mlsanity.com/paper/2310.11696/) (2023)
- [Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection](https://mlsanity.com/paper/2505.04594/) (2025)
- [SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection](https://mlsanity.com/paper/2305.07270/) (2023)
- [ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation](https://mlsanity.com/paper/2311.11106/) (2023)
- [SST: Real-time End-to-end Monocular 3D Reconstruction via Sparse Spatial-Temporal Guidance](https://mlsanity.com/paper/2212.06524/) (2022)
- [Towards Intrinsic-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2603.27059/) (2026)
- [GSDC Transformer: An Efficient and Effective Cue Fusion for Monocular Multi-Frame Depth Estimation](https://mlsanity.com/paper/2309.17059/) (2023)
- [Resolving Symmetry Ambiguity in Correspondence-based Methods for Instance-level Object Pose Estimation](https://mlsanity.com/paper/2405.10557/) (2024)
- [LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection](https://mlsanity.com/paper/2512.05663/) (2025)
- [Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations](https://mlsanity.com/paper/2211.07108/) (2022)
- [S3-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection](https://mlsanity.com/paper/2309.00928/) (2023)
- [Learning Collective Dynamics of Multi-Agent Systems using Event-based Vision](https://mlsanity.com/paper/2411.07039/) (2024)
- [MonoVQD: Monocular 3D Object Detection with Variational Query Denoising and Self-Distillation](https://mlsanity.com/paper/2506.14835/) (2025)
- [Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction](https://mlsanity.com/paper/2508.11282/) (2025)
- [Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising](https://mlsanity.com/paper/2601.01036/) (2026)
- [MonoPRIO: Adaptive Prior Conditioning for Unified Monocular 3D Object Detection](https://mlsanity.com/paper/2605.14781/) (2026)
- [MonoMIP: Multi-Height Inverse Perspective Mapping for Monocular 3D Object Detection](https://mlsanity.com/paper/2610.19071/) (2026)

## Abstract (arXiv)

Despite monocular 3D object detection having recently made a significant leap forward thanks to the use of pre-trained depth estimators for pseudo-LiDAR recovery, such two-stage methods typically suffer from overfitting and are incapable of explicitly encapsulating the geometric relation between depth and object bounding box. To overcome this limitation, we instead propose OPA-3D, a single-stage, end-to-end, Occlusion-Aware Pixel-Wise Aggregation network that to jointly estimate dense scene depth with depth-bounding box residuals and object bounding boxes, allowing a two-stream detection of 3D objects, leading to significantly more robust detections. Thereby, the geometry stream denoted as the Geometry Stream, combines visible depth and depth-bounding box residuals to recover the object bounding box via explicit occlusion-aware optimization. In addition, a bounding box based geometry projection scheme is employed in an effort to enhance distance perception. The second stream, named as the Context Stream, directly regresses 3D object location and size. This novel two-stream representation further enables us to enforce cross-stream consistency terms which aligns the outputs of both streams, improving the overall performance. Extensive experiments on the public benchmark demonstrate that OPA-3D outperforms state-of-the-art methods on the main Car category, whilst keeping a real-time inference speed. We plan to release all codes and trained models soon.