Awesome Monocular 3D detection

Paper list of 3D detetction, keep updating!

Contents

• Paper List
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
• KITTI Results

Paper List

2024

• [MonoCD] MonoCD: Monocular 3D Object Detection with Complementary Depths [CVPR2024][Pytorch]
• [DPL] Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection [CVPR2024]
• [UniMODE] UniMODE: Unified Monocular 3D Object Detection [CVPR2024]
• [YOLOBU] You Only Look Bottom-Up for Monocular 3D Object Detection [RA-L2024]

2023

• [DDML] Depth-discriminative Metric Learning for Monocular 3D Object Detection [NeurIPS2023]
• [MonoXiver] Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver [ICCV2023]
• [MonoNeRD] MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection [ICCV2023][Pytorch]
• [MonoATT] MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer [CVPR2023]
• [WeakMono3D] Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency [CVPR2023]
• [MonoPGC] MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts [ICRA2023]
• [ADD] Attention-based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection[AAAI2023]
• [MonoDETR] Depth-guided Transformer for Monocular 3D Object Detection[ICCV2023][Pytorch]

2022

• [MoGDE] MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation [NeurIPS2022]
• [LPCG] Lidar Point Cloud Guided Monocular 3D Object Detection [ECCV2022][Pytorch]
• [MVC-MonoDet] Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency [ECCV2022][Pytorch]
• [CMKD] Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection [ECCV2022][Pytorch]
• [DfM] Monocular 3D Object Detection with Depth from Motion [ECCV2022][Pytorch]
• [DEVIANT] DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection [ECCV2022][Pytorch]
• [DCD] Densely Constrained Depth Estimator for Monocular 3D Object Detection [ECCV2022][Pytorch]
• [STMono3D] Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training [ECCV2022]
• [DID-M3D] DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection [ECCV2022][Pytorch]
• [SGM3D] SGM3D: Stereo Guided Monocular 3D Object Detection [RA-L2022][Pytorch]
• [PRT] Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking [ICRA2022]
• [Time3D] Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving [CVPR2022]
• [MonoGround] MonoGround: Detecting Monocular 3D Objects from the Ground [CVPR2022][Pytorch]
• [DimEmbedding] Dimension Embeddings for Monocular 3D Object Detection [CVPR2022]
• [GeoAug] Exploring Geometric Consistency for Monocular 3D Object Detection [CVPR2022]
• [MonoDDE] Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection [CVPR2022]
• [Homography] Homography Loss for Monocular 3D Object Detection [CVPR2022]
• [Rope3D] Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task [CVPR2022][Pytorch]
• [MonoDTR] MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer [CVPR2022][Pytorch]
• [MonoJSG] MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection [CVPR2022][Pytorch]
• [Pseudo-Stereo] Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving [CVPR2022][Pytorch]
• [MonoDistill] MonoDistill: Learning Spatial Features for Monocular 3D Object Detection [ICLR2022][Pytorch]
• [WeakM3D] WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection [ICLR2022][Pytorch]
• [MonoCon] Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection [AAAI2022][Pytorch]
• [ImVoxelNet] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection [WACV2022][Pytorch]

2021

• [PCT] Progressive Coordinate Transforms for Monocular 3D Object Detection [NeurIPS2021][Pytorch]
• [DeepLineEncoding] Deep Line Encoding for Monocular 3D Object Detection and Depth Prediction [BMVC2021][Pytorch]
• [DFR-Net] The Devil Is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection [ICCV2021]
• [AutoShape] AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection [ICCV2021][Pytorch][Paddle]
• [pseudo-analysis] Are we Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection? [ICCV2021]
• [Gated3D] Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues [ICCV2021]
• [MonoRCNN] Geometry-based Distance Decomposition for Monocular 3D Object Detection [ICCV2021][Pytorch]
• [DD3D] Is Pseudo-Lidar needed for Monocular 3D Object detection [ICCV2021][Pytorch]
• [GUPNet] Geometry Uncertainty Projection Network for Monocular 3D Object Detection [ICCV2021][Pytorch]
• [Neighbor-Vote] Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting [ACMMM2021][Pytorch]
• [MonoEF] Monocular 3D Object Detection: An Extrinsic Parameter Free Approach [CVPR2021][Pytorch]
• [monodle] Delving into Localization Errors for Monocular 3D Object Detection [CVPR2021][Pytorch]
• [Monoflex] Objects are Different: Flexible Monocular 3D Object Detection [CVPR2021][Pytorch]
• [GrooMeD-NMS] GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection [CVPR2021][Pytorch]
• [DDMP-3D] Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection [CVPR2021][Pytorch]
• [MonoRUn] MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation [CVPR2021][Pytorch]
• [M3DSSD] M3DSSD: Monocular 3D Single Stage Object Detector [CVPR2021][Pytorch]
• [CaDDN] Categorical Depth Distribution Network for Monocular 3D Object Detection [CVPR2021][Pytorch]
• [visualDet3D] Ground-aware Monocular 3D Object Detection for Autonomous Driving [RA-L][Pytorch]

2020

• [UR3D] Distance-Normalized Unified Representation for Monocular 3D Object Detection [ECCV2020]
• [MonoDR] Monocular Differentiable Rendering for Self-Supervised 3D Object Detection [ECCV2020]
• [DA-3Ddet] Monocular 3d object detection via feature domain adaptation [ECCV2020]
• [MoVi-3D] Towards generalization across depth for monocular 3d object detection [ECCV2020]
• [PatchNet] Rethinking Pseudo-LiDAR Representation [ECCV2020][Pytorch]
• [RAR-Net] Reinforced Axial Refinement Network for Monocular 3D Object Detection [ECCV2020]
• [kinematic3d] Kinematic 3D Object Detection in Monocular Video [ECCV2020][Pytorch]
• [RTM3D] RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving [ECCV2020][Pytorch]
• [SMOKE] SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation [CVPRW2020][Pytorch]
• [D4LCN] Learning Depth-Guided Convolutions for Monocular 3D Object Detection [CVPRW2020][Pytorch]
• [MonoPair] MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships [CVPR2020]
• [pseudo-LiDAR_e2e] End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection [CVPR2020][Pytorch]
• [Pseudo-LiDAR++] Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving [ICLR2020][Pytorch]
• [OACV] Object-Aware Centroid Voting for Monocular 3D Object Detection [IROS2020]
• [MonoGRNet_v2] Monocular 3D Object Detection via Geometric Reasoning on Keypoints [VISIGRAPP2020]
• [ForeSeE] Task-Aware Monocular Depth Estimation for 3D Object Detection [AAAI2020(oral)][Pytorch]
• [Decoupled-3D] Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation [AAAI2020]

2019

• [3d-vehicle-tracking] Joint Monocular 3D Vehicle Detection and Tracking [ICCV2019][Pytorch]
• [MonoDIS] Disentangling monocular 3d object detection [ICCV2019]
• [AM3D] Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving [ICCV2019]
• [M3D-RPN] M3D-RPN: Monocular 3D Region Proposal Network for Object Detection [ICCV2019(Oral)][Pytorch]
• [MVRA] Multi-View Reprojection Architecture for Orientation Estimation [ICCVW2019]
• [Mono3DPLiDAR] Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud [ICCVW2019]
• [MonoPSR] Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction [CVPR2019][Pytorch]
• [FQNet] Deep fitting degree scoring network for monocular 3d object detection [CVPR2019]
• [ROI-10D] ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape [CVPR2019]
• [GS3D] GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving [CVPR2019]
• [Pseudo-LiDAR] Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving [CVPR2019][Pytorch]
• [BirdGAN] Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehicles [IROS2019]
• [MonoGRNet] MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization [AAAI2019(oral)][Tensorflow]
• [OFT-Net] Orthographic feature transform for monocular 3d object detection [BMVC2019][Pytorch]
• [Shift R-CNN] Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints [TIP2019]
• [SS3D] SS3D: Monocular 3d object detection and box fitting trained end-to-end using intersection-over-union loss [Arxiv2019]

2018

• [Multi-Fusion] Multi-Level Fusion based 3D Object Detection from Monocular Images [CVPR2018][Pytorch]
• [Mono3D++] Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors [AAAI2018]

2017

• [Deep3DBox] 3D Bounding Box Estimation Using Deep Learning and Geometry [CVPR2017][Pytorch][Tensorflow]
• [Deep MANTA] Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image [CVPR2017]

2016

• [Mono3D] Monocular 3D object detection for autonomous driving [CVPR2016]

KITTI Results

Method	Extra	Test, AP3D|R40			Val, AP3D|R40			Reference
		Easy	Mod.	Hard	Easy	Mod.	Hard
LPCG	Lidar+raw	25.56	17.80	15.38	31.15	23.42	20.60	ECCV2022
CMKD	Lidar+raw	28.55	18.69	16.77	-	-	-	ECCV2022
MonoPSR	Lidar	10.76	7.25	5.85	-	-	-	CVPR2019
MonoRUn	Lidar	19.65	12.30	10.58	20.02	14.65	12.61	CVPR2021
CaDDN	Lidar	19.17	13.41	11.46	23.57	16.31	13.84	CVPR2021
MonoDistill	Lidar	22.97	16.03	13.60	24.31	18.47	15.76	ICLR2022
AM3D	Depth	16.50	10.74	9.52	28.31	15.76	12.24	ICCV2019
PatchNet	Depth	15.68	11.12	10.17	31.60	16.80	13.80	ECCV2020
D4LCN	Depth	16.65	11.72	9.51	22.32	16.20	12.30	CVPRW2020
DFR-Net	Depth	19.40	13.63	10.35	24.81	17.78	14.41	ICCV2021
Pseudo-Stereo	Depth	23.74	17.74	15.14	35.18	24.15	20.35	CVPR2022
M3D-RPN	None	14.76	9.71	7.42	14.53	11.07	8.65	ICCV2019
SMOKE	None	14.03	9.76	7.84	-	-	-	CVPRW2020
MonoPair	None	13.04	9.99	8.65	16.28	12.30	10.42	CVPR2020
RTM3D	None	14.41	10.34	8.77	-	-	-	ECCV2020
M3DSSD	None	17.51	11.46	8.98	-	-	-	CVPR2021
Monoflex	None	19.94	13.89	12.07	23.64	17.51	14.83	CVPR2021
GUPNet	None	20.11	14.20	11.77	22.76	16.46	13.72	ICCV2021
MonoCon	None	22.50	16.46	13.95	26.33	19.01	15.98	AAAI2022
MonoDDE	None	24.93	17.14	15.10	26.66	19.75	16.72	CVPR2022
MonoXiver	None	25.24	19.04	16.39	30.48	22.40	19.13	ICCV2023