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.
A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting
RAP-SAM: Towards Real-Time All-Purpose Segment Anything
OMG-Seg: Is One Model Good Enough For All Segmentation?
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding
Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering
Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation
3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation
Contextual Associated Triplet Queries for Panoptic Scene Graph Generation
Unsupervised Universal Image Segmentation
EfficientPPS: Part-aware Panoptic Segmentation of Transparent Objects for Robotic Manipulation
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation
GIVT: Generative Infinite-Vocabulary Transformers
Aligning and Prompting Everything All at Once for Universal Visual Perception
Digital Histopathology with Graph Neural Networks: Concepts and Explanations for Clinicians
A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentation
Panoptic Video Scene Graph Generation
Seeing Eye to AI: Comparing Human Gaze and Model Attention in Video Memorability
OneFormer3D: One Transformer for Unified Point Cloud Segmentation
Self-trained Panoptic Segmentation
Center Focusing Network for Real-Time LiDAR Panoptic Segmentation
ASSIST: Interactive Scene Nodes for Scalable and Realistic Indoor Simulation
SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis
4D-Former: Multimodal 4D Panoptic Segmentation
Lidar Panoptic Segmentation and Tracking without Bells and Whistles
Panoptic Out-of-Distribution Segmentation
Hierarchical Mask2Former: Panoptic Segmentation of Crops, Weeds and Leaves
SimPLR: A Simple and Plain Transformer for Scaling-Efficient Object Detection and Segmentation
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
Mask4Former: Mask Transformer for 4D Panoptic Segmentation
Finite Scalar Quantization: VQ-VAE Made Simple
A SAM-based Solution for Hierarchical Panoptic Segmentation of Crops and Weeds Competition
PanopticNDT: Efficient and Robust Panoptic Mapping
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.