Panoptic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 27
- 보존된 평가 기록
- 207
Panoptic Segmentation is a computer vision task that combines semantic segmentation and instance segmentation to provide a comprehensive understanding of the scene. The goal of panoptic segmentation is to segment the image into semantically meaningful parts or regions, while also detecting and distinguishing individual instances of objects within those regions. In a given image, every pixel is assigned a semantic label, and pixels belonging to "things" classes (countable objects with instances, like cars and people) are assigned unique instance IDs. <span style="color:grey; opacity: 0.6">( Image credit: Detectron2 )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer Model
Open-World Panoptic Segmentation
Volumetric Mapping with Panoptic Refinement via Kernel Density Estimation for Mobile Robots
PanSR: An Object-Centric Mask Transformer for Panoptic Segmentation
EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation
Balancing Shared and Task-Specific Representations: A Hybrid Approach to Depth-Aware Video Panoptic Segmentation
Panoptic Diffusion Models: co-generation of images and segmentation maps
LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention
HyperSeg: Towards Universal Visual Segmentation with Large Language Model
Weakly supervised image segmentation for defect-based grading of fresh produce
MGNiceNet: Unified Monocular Geometric Scene Understanding
Agricultural Landscape Understanding At Country-Scale
PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting
Configurable Embodied Data Generation for Class-Agnostic RGB-D Video Segmentation
PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion
CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes
In-Place Panoptic Radiance Field Segmentation with Perceptual Prior for 3D Scene Understanding
Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks
Adapting Vision-Language Model with Fine-grained Semantics for Open-Vocabulary Segmentation
Lidar Panoptic Segmentation in an Open World
@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology
Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model
Panoptic-Depth Forecasting
Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation
Dynamic Prompting of Frozen Text-to-Image Diffusion Models for Panoptic Narrative Grounding
Towards Localizing Structural Elements: Merging Geometrical Detection with Semantic Verification in RGB-D Data
A Simple and Generalist Approach for Panoptic Segmentation
DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries
Image Segmentation in Foundation Model Era: A Survey
NuLite -- Lightweight and Fast Model for Nuclei Instance Segmentation and Classification
LKCell: Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels
SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation
MC-PanDA: Mask Confidence for Panoptic Domain Adaptation
Panoptic Segmentation of Mammograms with Text-To-Image Diffusion Model
OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.