Papers with Code 아카이브

Monocular 3D Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 16
보존된 평가 기록: 72

Monocular 3D Object Detection is the task to draw 3D bounding box around objects in a single 2D RGB image. It is localization task but without any extra information like depth or other sensors or multiple-images.

코드

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

https://github.com/zongdai/autoshape

공식 코드

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

https://github.com/zrrskywalker/monodetr

공식 코드

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

https://github.com/2gunsu/monocon-pytorch

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection

https://github.com/AllenPeng0209/deeproute_competition

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

https://github.com/Chenzixi1/D4LCNpaddle

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

https://github.com/Discover304/MMDetection3D-Eloss

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

https://github.com/Hansxsourse/Cross-Modality-Knowledge-Distillation-for-Multi-modal-Aerial-View-Object-Classification

https://github.com/Hongbin98/MonoTTA

Fully Test-Time Adaptation for Monocular 3D Object Detection

https://github.com/JuliaChae/M3D-RPN-Waymo

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

https://github.com/Nicholasli1995/EgoNet

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

https://github.com/PaddlePaddle/Paddle3D

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

https://github.com/Traffic-X/MonoUNI

https://github.com/WARM-3D/WARM-3D

WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection

https://github.com/ZhixinLai/3D-detection-with-monocular-RGB-image

Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction

https://github.com/abhi1kumar/M3D-RPN

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

https://github.com/abhi1kumar/seabird

DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

https://github.com/bosszhe/vimi

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

https://github.com/chetanmreddy/voxelnet_chetan

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

https://github.com/cxmomo/Neighbor-Vote

Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting

https://github.com/destinyls/SMOKE

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

https://github.com/garrickbrazil/kinematic3d

Kinematic 3D Object Detection in Monocular Video

https://github.com/jhkim-spa/FVNet_v2

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

https://github.com/konyul/mmdet3d

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

https://github.com/mit-han-lab/sparsevit

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

https://github.com/thusiyuan/holistic_scene_parsing

Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image

https://github.com/tom-roddick/oft

Orthographic Feature Transform for Monocular 3D Object Detection

https://github.com/tri-ml/vedet

Is Pseudo-Lidar needed for Monocular 3D Object detection?

https://github.com/vision-agh/pointpillars-backbone

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

https://github.com/vision-agh/pointpillars_backbone

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

https://github.com/yhbcode000/MMDetection3D-Eloss

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

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