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 Fair Ranking and New Model for Panoptic Scene Graph Generation
Panoptic Segmentation of Galactic Structures in LSB Images
Context-Aware Video Instance Segmentation
Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Tasks
PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction
Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation
Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations
PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving
1st Place Winner of the 2024 Pixel-level Video Understanding in the Wild (CVPR'24 PVUW) Challenge in Video Panoptic Segmentation and Best Long Video Consistency of Video Semantic Segmentation
3rd Place Solution for PVUW Challenge 2024: Video Panoptic Segmentation
2nd Place Solution for PVUW Challenge 2024: Video Panoptic Segmentation
A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation
An Integrated Framework for Multi-Granular Explanation of Video Summarization
4D Panoptic Scene Graph Generation
Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception
Panoptic Segmentation and Labelling of Lumbar Spine Vertebrae using Modified Attention Unet
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies
The revenge of BiSeNet: Efficient Multi-Task Image Segmentation
COCONut: Modernizing COCO Segmentation
Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation
JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments
Using Images as Covariates: Measuring Curb Appeal with Deep Learning
ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model
Better Call SAL: Towards Learning to Segment Anything in Lidar
PosSAM: Panoptic Open-vocabulary Segment Anything
Small, Versatile and Mighty: A Range-View Perception Framework
PEM: Prototype-based Efficient MaskFormer for Image Segmentation
UniVS: Unified and Universal Video Segmentation with Prompts as Queries
Benchmarking the Robustness of Panoptic Segmentation for Automated Driving
Generalizable Semantic Vision Query Generation for Zero-shot Panoptic and Semantic Segmentation
Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review
Generalizable Entity Grounding via Assistance of Large Language Model
UrbanGenAI: Reconstructing Urban Landscapes using Panoptic Segmentation and Diffusion Models
Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.