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/hlsheng1/ct3d

공식 코드

Improving 3D Object Detection with Channel-wise Transformer

https://github.com/hlsheng1/ct3d-plusplus

공식 코드

CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer

https://github.com/hlsheng1/rdiou

공식 코드

Rethinking IoU-based Optimization for Single-stage 3D Object Detection

https://github.com/hoiliu-0801/monotakd

공식 코드

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection

https://github.com/hollow-503/unim2ae

공식 코드

UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving

https://github.com/hou-yz/MVDet

공식 코드

Multiview Detection with Feature Perspective Transformation

https://github.com/hou-yz/mvdetr

공식 코드

Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)

https://github.com/huaaaliu/rgbx_semantic_segmentation

공식 코드

CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers

https://github.com/huangzhe885/codiff

공식 코드

CoDiff: Conditional Diffusion Model for Collaborative 3D Object Detection

https://github.com/huawei-noah/noah-research/tree/master/TokenFusion

공식 코드

Multimodal Token Fusion for Vision Transformers

https://github.com/hust-jy/dds3d

공식 코드

DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection

https://github.com/hustvl/mim4d

공식 코드

MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning

https://github.com/hvxlab/hvdetfusion

공식 코드

HVDetFusion: A Simple and Robust Camera-Radar Fusion Framework

https://github.com/hyeon-jo/interchange-transfer-kd

공식 코드

itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection

https://github.com/hyjhkoh/mgtanet

공식 코드

MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection

https://github.com/ika-rwth-aachen/multicorrupt

공식 코드

MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object Detection

https://github.com/iliiliiliili/tanet-near-far

공식 코드

Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems

https://github.com/iranqin/supfusion

공식 코드

SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection

https://github.com/iseri27/tg_gbc

공식 코드

Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning

https://github.com/jacky121298/wlst

공식 코드

WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection

https://github.com/jbji/repvf

공식 코드

RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception

https://github.com/jeetv/gmvd

공식 코드

Bringing Generalization to Deep Multi-View Pedestrian Detection

https://github.com/jgwak/GSDN

공식 코드

Generative Sparse Detection Networks for 3D Single-shot Object Detection

https://github.com/jiadingcn/geminifusion

공식 코드

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

https://github.com/jialeli1/from-voxel-to-point

공식 코드

From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder

https://github.com/jialeli1/mgaf-3dssd

공식 코드

Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud

https://github.com/jiayuzou2020/diffbev

공식 코드

DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception

https://github.com/jimas95/CMinMax

공식 코드

cMinMax: A Fast Algorithm to Find the Corners of an N-dimensional Convex Polytope

https://github.com/jinlong17/bds-v2v

공식 코드

Breaking Data Silos: Cross-Domain Learning for Multi-Agent Perception from Independent Private Sources

https://github.com/jinlong17/v2vlc

공식 코드

Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communication

https://github.com/jo-wang/dpo

공식 코드

DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection

https://github.com/junhyung-SPALab/D-Align

공식 코드

D-Align: Dual Query Co-attention Network for 3D Object Detection Based on Multi-frame Point Cloud Sequence

https://github.com/junjie18/cmt

공식 코드

Cross Modal Transformer: Towards Fast and Robust 3D Object Detection

https://github.com/kaist-avelab/k-radar

공식 코드

K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions

https://github.com/kaixinbear/CAPE

공식 코드

CAPE: Camera View Position Embedding for Multi-View 3D Object Detection

https://github.com/kcyu2014/lidar-camera-robust-benchmark

공식 코드

Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection

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