# PanSt3R: Multi-view Consistent Panoptic Segmentation

arXiv: https://arxiv.org/abs/2506.21348 · HTML: https://mlsanity.com/paper/2506.21348/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 73 of its 88 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 30 of 73)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [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)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [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)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation](https://mlsanity.com/paper/2003.07853/) (2020)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)

## Built on by (most cited first, 20 of 20)

- [IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction](https://mlsanity.com/paper/2510.22706/) (2025)
- [AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend](https://mlsanity.com/paper/2511.20343/) (2025)
- [Unified Semantic Transformer for 3D Scene Understanding](https://mlsanity.com/paper/2512.14364/) (2025)
- [OccAny: Generalized Unconstrained Urban 3D Occupancy](https://mlsanity.com/paper/2603.23502/) (2026)
- [MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors](https://mlsanity.com/paper/2512.15577/) (2025)
- [3AM: 3egment Anything with Geometric Consistency in Videos](https://mlsanity.com/paper/2601.08831/) (2026)
- [FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation](https://mlsanity.com/paper/2603.25993/) (2026)
- [Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models](https://mlsanity.com/paper/2605.24642/) (2026)
- [SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images](https://mlsanity.com/paper/2603.19926/) (2026)
- [Dynamic Visual SLAM using a General 3D Prior](https://mlsanity.com/paper/2512.06868/) (2025)
- [Investigating Anthropometric Fidelity in SAM 3D Body](https://mlsanity.com/paper/2601.06035/) (2025)
- [Pano3D: Unified 3D Reconstruction and Panoptic Segmentation](https://mlsanity.com/paper/2606.14307/) (2026)
- [Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views](https://mlsanity.com/paper/2606.29513/) (2026)
- [Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison](https://mlsanity.com/paper/2609.01530/) (2026)
- [PanoSeg3R: Feed-Forward 3D Semantic Segmentation for Panoramic Images with an Automatic Data Curation Pipeline](https://mlsanity.com/paper/2609.22687/) (2026)
- [SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation](https://mlsanity.com/paper/2609.25490/) (2026)
- [Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation](https://mlsanity.com/paper/2607.19765/) (2026)
- [S4VY: Segment Anything in Feed-Forward 4D Visual Geometry](https://mlsanity.com/paper/2609.36875/) (2026)
- [RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation](https://mlsanity.com/paper/2610.00970/) (2026)
- [Every View Counts: View-Consistent Panoptic Quality for Multi-view Panoptic Segmentation](https://mlsanity.com/paper/2610.05911/) (2026)

## Abstract (arXiv)

Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing approaches typically leverage off-the-shelf models to extract per-frame 2D panoptic segmentations, before optimizing an implicit geometric representation (often based on NeRF) to integrate and fuse the 2D predictions. We argue that relying on 2D panoptic segmentation for a problem inherently 3D and multi-view is likely suboptimal as it fails to leverage the full potential of spatial relationships across views. In addition to requiring camera parameters, these approaches also necessitate computationally expensive test-time optimization for each scene. Instead, in this work, we propose a unified and integrated approach PanSt3R, which eliminates the need for test-time optimization by jointly predicting 3D geometry and multi-view panoptic segmentation in a single forward pass. Our approach builds upon recent advances in 3D reconstruction, specifically upon MUSt3R, a scalable multi-view version of DUSt3R, and enhances it with semantic awareness and multi-view panoptic segmentation capabilities. We additionally revisit the standard post-processing mask merging procedure and introduce a more principled approach for multi-view segmentation. We also introduce a simple method for generating novel-view predictions based on the predictions of PanSt3R and vanilla 3DGS. Overall, the proposed PanSt3R is conceptually simple, yet fast and scalable, and achieves state-of-the-art performance on several benchmarks, while being orders of magnitude faster than existing methods.