Papers with Code 아카이브

3D Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 67
보존된 평가 기록: 806

3D Object Detection is a task in computer vision where the goal is to identify and locate objects in a 3D environment based on their shape, location, and orientation. It involves detecting the presence of objects and determining their location in the 3D space in real-time. This task is crucial for applications such as autonomous vehicles, robotics, and augmented reality.

<span style="color:grey; opacity: 0.6">( Image credit: AVOD )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/XJTU-Haolin/TT3D

공식 코드

3D Harmonic Loss: Towards Task-consistent and Time-friendly 3D Object Detection on Edge for V2X Orchestration

https://github.com/Xianpeng919/MonoCon

공식 코드

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection

https://github.com/YinminZhang/MonoGeo

공식 코드

Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection

https://github.com/YoushaaMurhij/FMFNet

공식 코드

Real-time 3D Object Detection using Feature Map Flow

https://github.com/Yzichen/FlashOCC

공식 코드

FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin

https://github.com/Zengyi-Qin/MonoGRNet

공식 코드

MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization

https://github.com/Zengyi-Qin/Weakly-Supervised-3D-Object-Detection

공식 코드

Weakly Supervised 3D Object Detection from Point Clouds

https://github.com/a-nau/CubeRefine-R-CNN

공식 코드

Parcel3D: Shape Reconstruction from Single RGB Images for Applications in Transportation Logistics

https://github.com/a-nau/synthetic-dataset-generation

공식 코드

Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics

https://github.com/abhi1kumar/deviant

공식 코드

DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

https://github.com/abhi1kumar/groomed_nms

공식 코드

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

https://github.com/abhi1kumar/seabird

공식 코드

SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects

https://github.com/adept-thu/RoboFusion

공식 코드

RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAM

https://github.com/adept-thu/dual-radar

공식 코드

Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autonomous Driving

https://github.com/adlab-autodrive/bevfusion

공식 코드

BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework

https://github.com/adlab-autodrive/bevheight

공식 코드

BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection

https://github.com/adlab3ds/tig-bev

공식 코드

TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning

https://github.com/agent-sgs/pillarnet

공식 코드

PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

https://github.com/aharley/neural_3d_mapping

공식 코드

Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping

https://github.com/ai4ce/DiscoNet

공식 코드

Learning Distilled Collaboration Graph for Multi-Agent Perception

https://github.com/aimotive/aimotive-dataset-loader

공식 코드

aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range Perception

https://github.com/aimotive/aimotive_dataset

공식 코드

aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range Perception

https://github.com/air-discover/dqs3d

공식 코드

DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

https://github.com/air-thu/dair-rcooper

공식 코드

RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception

https://github.com/air-thu/dair-v2x

공식 코드

DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection

https://github.com/airotau/pointpillarshailoinnoviz

공식 코드

Real-Time 3D Object Detection Using InnovizOne LiDAR and Low-Power Hailo-8 AI Accelerator

https://github.com/ajedgley/rebound

공식 코드

ReBound: An Open-Source 3D Bounding Box Annotation Tool for Active Learning

https://github.com/alphaplustt/daocc

공식 코드

DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction

https://github.com/amazon-research/progressive-coordinate-transforms

공식 코드

Progressive Coordinate Transforms for Monocular 3D Object Detection

https://github.com/ansonlcy/TSceneJAL

공식 코드

TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detection

https://github.com/apple/ARKitScenes

공식 코드

ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data

https://github.com/arcaninez/odm3d

공식 코드

ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection

https://github.com/argoverse/av2-api

공식 코드

Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting

https://github.com/asterisci/point-gcc

공식 코드

Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast

https://github.com/augcog/dttd2

공식 코드

Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset

https://github.com/augcog/robust-digital-twin-tracking

공식 코드

Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.