# Every View Counts: View-Consistent Panoptic Quality for Multi-view Panoptic Segmentation

arXiv: https://arxiv.org/abs/2610.05911 · HTML: https://mlsanity.com/paper/2610.05911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 38 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 30 of 34)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Panoptic Lifting for 3D Scene Understanding with Neural Fields](https://mlsanity.com/paper/2212.09802/) (2022)
- [Video Panoptic Segmentation](https://mlsanity.com/paper/2006.11339/) (2020)
- [MUSt3R: Multi-view Network for Stereo 3D Reconstruction](https://mlsanity.com/paper/2503.01661/) (2025)
- [ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2012.05258/) (2020)
- [STEP: Segmenting and Tracking Every Pixel](https://mlsanity.com/paper/2102.11859/) (2021)
- [4D Panoptic LiDAR Segmentation](https://mlsanity.com/paper/2102.12472/) (2021)
- [Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion](https://mlsanity.com/paper/2306.04633/) (2023)
- [Waymo Open Dataset: Panoramic Video Panoptic Segmentation](https://mlsanity.com/paper/2206.07704/) (2022)
- [Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting](https://mlsanity.com/paper/2503.14029/) (2025)
- [IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction](https://mlsanity.com/paper/2510.22706/) (2025)
- [PanSt3R: Multi-view Consistent Panoptic Segmentation](https://mlsanity.com/paper/2506.21348/) (2025)
- [PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion](https://mlsanity.com/paper/2410.10659/) (2024)
- [SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment](https://mlsanity.com/paper/2507.02705/) (2025)
- [Visual object tracking performance measures revisited](https://mlsanity.com/paper/1502.05803/) (2015)
- [PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes](https://mlsanity.com/paper/2309.10815/) (2023)
- [Unified Semantic Transformer for 3D Scene Understanding](https://mlsanity.com/paper/2512.14364/) (2025)
- [FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation](https://mlsanity.com/paper/2603.25993/) (2026)
- [SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images](https://mlsanity.com/paper/2603.19926/) (2026)

## Abstract (arXiv)

Multi-view panoptic segmentation assigns a semantic class and a scene-level instance ID to every pixel of an unordered set of images, and recent feed-forward 3D models predict these labels for the input views in a single forward pass. Their predictions, however, have been evaluated with the scene-level PQ (PQ^scene) borrowed from per-scene optimization methods, typically on rendered held-out views. PQ^scene tiles all views of a scene into a single image, so that a missed appearance or a change of ID lowers the score of the matched pair only in proportion to its area. We propose View-Consistent Panoptic Quality (VC-PQ), which extends PQ from a single image to a set of input views, counts equally every view in which an instance is visible, and penalizes a prediction that is not visible in the same views as its ground truth. A decomposition of VC-PQ attributes the score a method loses to mask accuracy, view consistency, and the matching threshold. A single additional parameter recovers the area weighting of tiling for comparison. Under a fixed evaluation protocol on ScanNet++ and ScanNetv2, recent feed-forward methods are evaluated with VC-PQ and PQ^scene, and the decomposition shows where each of them loses its score. Controlled perturbations of the ground truth show that VC-PQ responds to the number of views in which an instance is missed or changes ID, whereas PQ^scene responds to their area. The aim of this work is to make view consistency part of the evaluation of multi-view panoptic segmentation, with VC-PQ reported alongside PQ^scene. The evaluation code and the input sets of the protocol are available at https://github.com/Renem24/vcpq.