Papers with Code 아카이브

3D Semantic Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 19
보존된 평가 기록: 145

3D Semantic Segmentation is a computer vision task that involves dividing a 3D point cloud or 3D mesh into semantically meaningful parts or regions. The goal of 3D semantic segmentation is to identify and label different objects and parts within a 3D scene, which can be used for applications such as robotics, autonomous driving, and augmented reality.

코드

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

https://github.com/WangYueFt/dgcnn

공식 코드

Dynamic Graph CNN for Learning on Point Clouds

https://github.com/WeikaiTan/Toronto-3D

공식 코드

Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways

https://github.com/Xiangxu-0103/FRNet

공식 코드

FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation

https://github.com/Yacovitch/EyeNet

공식 코드

Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene

https://github.com/aboulch/ConvPoint

공식 코드

ConvPoint: Continuous Convolutions for Point Cloud Processing

https://github.com/ajhamdi/vointcloud

공식 코드

Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding

https://github.com/andrewcaunes/ia4markings

공식 코드

seg_3D_by_PC2D: Multi-View Projection for Domain Generalization and Adaptation in 3D Semantic Segmentation

https://github.com/aroncao49/mopa

공식 코드

MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation

https://github.com/arvindmvepa/al-seg

공식 코드

Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation

https://github.com/asbjrnmunk/amaes

공식 코드

AMAES: Augmented Masked Autoencoder Pretraining on Public Brain MRI Data for 3D-Native Segmentation

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

공식 코드

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

https://github.com/ayushjain1144/odin

공식 코드

ODIN: A Single Model for 2D and 3D Segmentation

https://github.com/azhuantou/aiscene

공식 코드

Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation

https://github.com/barcaaaa/ftd-plusplus

공식 코드

Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation

https://github.com/blue-531/talos

공식 코드

TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight

https://github.com/buildingnet/buildingnet_dataset

공식 코드

BuildingNet: Learning to Label 3D Buildings

https://github.com/chaytonmin/occupancy-mae

공식 코드

Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

https://github.com/chaytonmin/voxel-mae

공식 코드

Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

https://github.com/chenfengxu714/SqueezeSegV3

공식 코드

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

https://github.com/christophreich1996/3d_baggage_segmentation

공식 코드

Scalable 3D Semantic Segmentation for Gun Detection in CT Scans

https://github.com/christophreich1996/oss-net

공식 코드

OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data

https://github.com/chuhang/SurfConv

공식 코드

SurfConv: Bridging 3D and 2D Convolution for RGBD Images

https://github.com/csiro-robotics/WildScenes

공식 코드

WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments

https://github.com/ctu-vras/t-concord3d

공식 코드

Teachers in concordance for pseudo-labeling of 3D sequential data

https://github.com/ctu-vras/t-uda

공식 코드

T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds

https://github.com/cv-rits/coarse3d

공식 코드

COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation

https://github.com/cvg/labelmaker

공식 코드

ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding

https://github.com/cvlab-unibo/mm2d3d

공식 코드

Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentation

https://github.com/cvmi-lab/doda

공식 코드

DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation

https://github.com/cvmi-lab/mars3d

공식 코드

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

https://github.com/drprojects/deepviewagg

공식 코드

Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation

https://github.com/drprojects/superpoint_transformer

공식 코드

Efficient 3D Semantic Segmentation with Superpoint Transformer

https://github.com/dvlab-research/sphereformer

공식 코드

Spherical Transformer for LiDAR-based 3D Recognition

https://github.com/eaphan/nclr

공식 코드

Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration

https://github.com/edwardzhou130/PolarSeg

공식 코드

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation

https://github.com/etrontech/vfmseg

공식 코드

Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

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