Panoptic Segmentation
27개 벤치마크 · 논문 505편 · 이 태스크의 논문 보기 →
Benchmarks
COCO test-dev
Cityscapes val
COCO minival
ADE20K val
Mapillary val
Cityscapes test
LaRS
S3DIS Area5
ScanNetV2
Indian Driving Dataset
KITTI Panoptic Segmentation
PanNuke
ScanNet
PASTIS
COCO panoptic
NYU Depth v2
SemanticKITTI
ADE20K
DALES
Hypersim
KITTI-360
PASTIS-R
Panoptic nuScenes test
Panoptic nuScenes val
S3DIS
SUN-RGBD
Most implemented
Mask R-CNN
End-to-End Object Detection with Transformers
ResNeSt: Split-Attention Networks
Visual Attention Network
PVT v2: Improved Baselines with Pyramid Vision Transformer
SOLOv2: Dynamic and Fast Instance Segmentation
Papers
GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure
3D object detection from LiDAR point clouds is a core problem in autonomous driving. Recent advances in self-supervised learning (SSL) enable scalable pretraining and transfers well to per-point tasks such as semantic an…
Self-Supervised LearningRepresentation LearningPanoptic Segmentation3D Object DetectionExtending a Large View Synthesis Model for Multi-view Panoptic Segmentation
Large view synthesis models synthesize novel views through cross-view attention without explicit 3D representations, and recent studies have shown that they learn accurate spatial correspondence from RGB supervision alon…
Panoptic SegmentationNovel View SynthesisScene Understanding3D ReconstructionInstance-Enriched Semantic Maps for Visual Language Navigation
Visual Language Navigation (VLN) aims to enable an embodied agent to navigate complex environments by following natural language instructions. Recent approaches build semantic spatial maps and leverage Large Language Mod…
Panoptic SegmentationDecision MakingDM-KG: A Novel Method for Boosting Spatial Cognition of Vision-Language Models in Street View Imagery
As vision-language models (VLMs) are increasingly deployed in geospatial question answering and visual scene understanding, improving their spatial cognition capability on street view imagery for complex logical reasonin…
Visual Question AnsweringPanoptic SegmentationScene UnderstandingSpatial ReasoningPano3D: Unified 3D Reconstruction and Panoptic Segmentation
Recent advances in 3D feedforward reconstruction neural networks have achieved remarkable success in dense reconstruction from images without any camera parameters. Yet, equipping these models with robust semantic unders…
Panoptic Segmentation3D ReconstructionEPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
This paper introduces EPS3D, a new end-to-end feed-forward framework for open-vocabulary 3D panoptic segmentation. Unlike existing methods relying on additional preprocessing, we design an end-to-end architecture, with a…
Panoptic SegmentationScene Understanding3D scene Editing