3D Semantic Segmentation
169 papers with code • 14 benchmarks • 31 datasets
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.
Benchmarks
These leaderboards are used to track progress in 3D Semantic Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Semantic Segmentation models and implementationsDatasets
nuScenes
SemanticKITTI
S3DIS
KITTI-360
PartNet
SemanticPOSS
AMOS
RELLIS-3D
STPLS3D
nuScenes-C
Subtasks
Latest papers
FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation
LiDAR segmentation has become a crucial component in advanced autonomous driving systems.
OneFormer3D: One Transformer for Unified Point Cloud Segmentation
Semantic, instance, and panoptic segmentation of 3D point clouds have been addressed using task-specific models of distinct design.
GNeSF: Generalizable Neural Semantic Fields
hlinchen/gnesf
•
•
NeurIPS 2023
We propose a novel soft voting mechanism to aggregate the 2D semantic information from different views for each 3D point.
Vision Transformers increase efficiency of 3D cardiac CT multi-label segmentation
ljollans/trunet
•
•
Accurate segmentation of the heart is essential for personalized blood flow simulations and surgical intervention planning.
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
In this paper, we introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation, thereby establishing a pathway to 3D foundational models.
UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
In the context of autonomous driving, the significance of effective feature learning is widely acknowledged.
Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset
Using our dataset and annotations, we release benchmarks for 3D object detection and 3D semantic segmentation using established metrics.
MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation
In this work, we propose Multi-modal Prior Aided (MoPA) domain adaptation to improve the performance of rare objects.
T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds
ctu-vras/t-uda
•
•
Deep perception models have to reliably cope with an open-world setting of domain shifts induced by different geographic regions, sensor properties, mounting positions, and several other reasons.
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
Besides, we construct the OpenPCSeg codebase, which is the largest and most comprehensive outdoor LiDAR segmentation codebase.
