Every View Counts: View-Consistent Panoptic Quality for Multi-view Panoptic Segmentation
cs.CV
Submitted: 2026-10-05
Updated: 2026-10-15
Code: https://github.com/cocodataset/panopticapi
Sources
- 4D Panoptic LiDAR Segmentation
- Pano3D: Unified 3D Reconstruction and Panoptic Segmentation
- MUSt3R: Multi-view Network for Stereo 3D Reconstruction
- Visual object tracking performance measures revisited
- UniC-Lift: Unified 3D Instance Segmentation via Contrastive Learning
- PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
- InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding
- Video Panoptic Segmentation
- Unified Semantic Transformer for 3D Scene Understanding
- Grounding Image Matching in 3D with MASt3R
- Language-driven Semantic Segmentation
- FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation
- IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
- Waymo Open Dataset: Panoramic Video Panoptic Segmentation
- ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
- SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images
- STEP: Segmenting and Tracking Every Pixel
- SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
- G$^2$TAM: Geometry Grounded Track Anything Model
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models