3D

Papers

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

• intro: CVPR 2019
• arxiv: https://arxiv.org/abs/1904.05866
• project page: https://smpl-x.is.tue.mpg.de/
• github: https://github.com/vchoutas/smplify-x

Collaborative Regression of Expressive Bodies using Moderation

• intro: PIXIE
• project page: https://pixie.is.tue.mpg.de/
• arxiv: https://arxiv.org/abs/2105.05301
• github: https://github.com/YadiraF/PIXIE

Hand Image Understanding via Deep Multi-Task Learning

• intro: ICCV 2021
• arxiv: https://arxiv.org/abs/2107.11646

VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild

https://arxiv.org/abs/2108.02452

EventHPE: Event-based 3D Human Pose and Shape Estimation

• intro: ICCV 2021
• intro: University of Alberta & Shandong University & Celepixel Technology & University of Guelph & Nanyang Technological University
• arxiv: https://arxiv.org/abs/2108.06819

Monocular 3D Object Detection

Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss

• keywords: SS3D
• arxiv: https://arxiv.org/abs/1906.08070
• video: https://www.youtube.com/playlist?list=PL4jJwJr7UjMb4bzLwUGHdVmhfNS2Ads_x

M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

• intro: ICCV 2019 oral
• project page: http://cvlab.cse.msu.edu/project-m3d-rpn.html
• arxiv: https://arxiv.org/abs/1907.06038
• github: https://github.com/garrickbrazil/M3D-RPN

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

• intro: CVPR 2020
• arxiv: https://arxiv.org/abs/1912.04799
• github: https://github.com/dingmyu/D4LCN

RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving

• intro: ECCV 2020
• arxiv: https://arxiv.org/abs/2001.03343

SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

• intro: CVPR 2020
• intro: ZongMu Tech & TU/e
• arxiv: https://arxiv.org/abs/2002.10111
• github(official): https://github.com/lzccccc/SMOKE

Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understanding

• keywords: one-stage anchor-free
• arxiv: https://arxiv.org/abs/2005.13423

Monocular Differentiable Rendering for Self-Supervised 3D Object Detection

• intro: ECCV 2020
• intro: Preferred Networks, Inc & Toyota Research Institute
• arxiv: https://arxiv.org/abs/2009.14524

M3DSSD: Monocular 3D Single Stage Object Detector

• intro: CVPR 2021
• intro: Zhejiang University & Mohamed bin Zayed University of Artificial Intelligence & Inception Institute of Artificial Intelligence
• arxiv: https://arxiv.org/abs/2103.13164

Delving into Localization Errors for Monocular 3D Object Detection

• intro: CVPR 2021
• arxiv: https://arxiv.org/abs/2103.16237
• github: https://github.com/xinzhuma/monodle

Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection

• github: CVPR 2021
• arxiv: https://arxiv.org/abs/2103.16470
• github: https://github.com/fudan-zvg/DDMP

GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection

• intro: CVPR 2021
• arxiv: https://arxiv.org/abs/2103.17202

Objects are Different: Flexible Monocular 3D Object Detection

• intro: CVPR 2021
• arxiv: https://arxiv.org/abs/2104.02323
• github: https://github.com/zhangyp15/MonoFlex

Geometry-based Distance Decomposition for Monocular 3D Object Detection

https://arxiv.org/abs/2104.03775

Geometry-aware data augmentation for monocular 3D object detection

https://arxiv.org/abs/2104.05858

OCM3D: Object-Centric Monocular 3D Object Detection

https://arxiv.org/abs/2104.06041

Exploring 2D Data Augmentation for 3D Monocular Object Detection

https://arxiv.org/abs/2104.10786

Progressive Coordinate Transforms for Monocular 3D Object Detection

• intro: Fudan University & Amazon Inc.
• arxiv: https://arxiv.org/abs/2108.05793
• github: https://github.com/amazon-research/progressive-coordinate-transforms

AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection

• intro: ICCV 2021
• intro: Baidu Research
• arxiv: https://arxiv.org/abs/2108.11127
• github: https://github.com/zongdai/AutoShape

Categorical Depth Distribution Network for Monocular 3D Object Detection

• intro: CVPR 2021 oral
• intro: University of Toronto Robotics Institute
• project page: https://trailab.github.io/CaDDN/
• arxiv: https://arxiv.org/abs/2103.01100
• github: https://github.com/TRAILab/CaDDN

The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection

• intro: ICCV 2021
• arxiv: https://arxiv.org/abs/2112.14023

SGM3D: Stereo Guided Monocular 3D Object Detection

• intro: Fudan University & Baidu Inc.
• arxiv: https://arxiv.org/abs/2112.01914
• github: https://github.com/zhouzheyuan/sgm3d

MonoDistill: Learning Spatial Features for Monocular 3D Object Detection

• intro: ICLR 2022
• intro: Dalian University of Technology & The University of Sydney
• arxiv: https://arxiv.org/abs/2201.10830
• github: https://github.com/monster-ghost/MonoDistill

Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving

• intro: CVPR 2022
• arxiv: https://arxiv.org/abs/2203.02112
• github:https://github.com/revisitq/Pseudo-Stereo-3D

MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection

• intro: CVPR 2022
• intro: The Hong Kong University of Science and Technology & DJI
• arxiv: https://arxiv.org/abs/2203.08563

MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer

• intro: CVPR 2022
• intro: National Taiwan University & Mobile Drive Technology
• arxiv: https://arxiv.org/abs/2203.10981
• github: https://github.com/kuanchihhuang/MonoDTR

MonoDETR: Depth-aware Transformer for Monocular 3D Object Detection

• intro: Shanghai AI Laboratory & Peking University & The Chinese University of Hong Kong
• arxiv: https://arxiv.org/abs/2203.13310

Homography Loss for Monocular 3D Object Detection

• intro: CVPR 2022
• arxiv: https://arxiv.org/abs/2204.00754

Towards Model Generalization for Monocular 3D Object Detection

• intro: Harbin Institute of Technology & University of Science and Technology of China & SenseTime Research
• arxiv: https://arxiv.org/abs/2205.11664

Delving into the Pre-training Paradigm of Monocular 3D Object Detection

• intro: Tsinghua University & Huazhong University of Science and Technology
• arxiv: https://arxiv.org/abs/2206.03657

MonoGround: Detecting Monocular 3D Objects from the Ground

• intro: CVPR 2022
• arxiv: https://arxiv.org/abs/2206.07372
• github: https://github.com/cfzd/MonoGround

Densely Constrained Depth Estimator for Monocular 3D Object Detection

• intro: ECCV 2022
• intro: CASIA & UCAS & HKISI CAS
• arxiv: https://arxiv.org/abs/2207.10047
• github:https://github.com/BraveGroup/DCD

Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection

• intro: DiDi
• arxiv: https://arxiv.org/abs/2207.07933

DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection

• intro: ECCV 2022
• intro: Zhejiang University & Fabu Inc.
• arxiv: https://arxiv.org/abs/2207.08531
• github: https://github.com/SPengLiang/DID-M3D

DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

• intro: ECCV 2022
• intro: Michigan State University & Meta AI & Ford Motor Company
• arxiv: https://arxiv.org/abs/2207.10758
• github: https://github.com/abhi1kumar/DEVIANT

Monocular 3D Object Detection with Depth from Motion

• intro: ECCV 2022 Oral
• intro: The Chinese University of Hong Kong & Shanghai AI Laboratory
• arxiv: https://arxiv.org/abs/2207.12988
• github: https://github.com/Tai-Wang/Depth-from-Motion

MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones

• intro: The Chinese University of Hong Kong & Hong Kong University of Science and Technology & The Chinese University of Hong Kong & 4Nanyang Technological University
• arxiv: https://arxiv.org/abs/2207.12716
• github: https://github.com/Tai-Wang/Depth-from-Motion

SEFormer: Structure Embedding Transformer for 3D Object Detection

• intro: Tsinghua University & Australian National University & National University of Singapore
• arxiv: https://arxiv.org/abs/2209.01745

Multi-Modal 3D Object Detection

AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection

• intro: IJCAI 2022
• intro: University of Science and Technology & Harbin Institute of Technology & SenseTime Research & The Chinese University of Hong Kong & Tsinghua University
• arxiv: https://arxiv.org/abs/2201.06493

AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection

• intro: ECCV 2022
• intro: University of Science and Technology of China & Harbin Institute of Technology & SenseTime Research
• arxiv: https://arxiv.org/abs/2207.10316
• github: https://github.com/zehuichen123/AutoAlignV2

Monocular 3D Detection and Tracking

Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving

• intro: CVPR 2022
• intro: PP-CEM & Rising Auto
• arxiv: https://arxiv.org/abs/2205.14882

Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking

• intro: Waymo LLC & Johns Hopkins University & Cornell University
• arxiv: https://arxiv.org/abs/2206.03666

Multi-Camera 3D Object Detection

PETR: Position Embedding Transformation for Multi-View 3D Object Detection

• intro: MEGVII Technology
• arxiv: https://arxiv.org/abs/2203.05625

PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

• intro: MEGVII Technology
• arxiv: https://arxiv.org/abs/2206.01256

Sparse4D

Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion

• intro: Horizon Robotics
• arxiv: https://arxiv.org/abs/2211.10581
• github: https://github.com/linxuewu/Sparse4D

Sparse4D v2: Recurrent Temporal Fusion with Sparse Model

• intro: Horizon Robotics
• arxiv: https://arxiv.org/abs/2305.14018
• github: https://github.com/linxuewu/Sparse4D

Sparse4D v3: Advancing End-to-End 3D Detection and Tracking

• intro: Horizon Robotics
• arxiv: https://arxiv.org/abs/2311.11722
• github: https://github.com/linxuewu/Sparse4D

Multi-Camera Multiple 3D Object Tracking

Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles

• intro: CVPR Workshop 2022
• arxiv: https://arxiv.org/abs/2204.09151

SRCN3D: Sparse R-CNN 3D Surround-View Camera Object Detection and Tracking for Autonomous Driving

• intro: Tsinghua University
• arxiv: https://arxiv.org/abs/2206.14451
• github: https://github.com/synsin0/SRCN3D