# PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion

arXiv: https://arxiv.org/abs/2410.10659 · HTML: https://mlsanity.com/paper/2410.10659/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 52 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 30 of 39)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [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)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [K-Net: Towards Unified Image Segmentation](https://mlsanity.com/paper/2106.14855/) (2021)
- [Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations](https://mlsanity.com/paper/2209.03494/) (2022)
- [Panoptic Lifting for 3D Scene Understanding with Neural Fields](https://mlsanity.com/paper/2212.09802/) (2022)
- [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://mlsanity.com/paper/2002.12212/) (2020)
- [3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans](https://mlsanity.com/paper/2002.06289/) (2020)
- [Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation](https://mlsanity.com/paper/2109.09881/) (2021)
- [Seamless Scene Segmentation](https://mlsanity.com/paper/1905.01220/) (2019)

## Built on by (most cited first, 16 of 16)

- [Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting](https://mlsanity.com/paper/2503.14029/) (2025)
- [PanSt3R: Multi-view Consistent Panoptic Segmentation](https://mlsanity.com/paper/2506.21348/) (2025)
- [PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding](https://mlsanity.com/paper/2503.18107/) (2025)
- [Tackling View-Dependent Semantics in 3D Language Gaussian Splatting](https://mlsanity.com/paper/2505.24746/) (2025)
- [COS3D: Collaborative Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2510.20238/) (2025)
- [MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors](https://mlsanity.com/paper/2512.15577/) (2025)
- [Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation](https://mlsanity.com/paper/2512.22745/) (2025)
- [EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation](https://mlsanity.com/paper/2606.08980/) (2026)
- [NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds](https://mlsanity.com/paper/2411.17392/) (2024)
- [OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting](https://mlsanity.com/paper/2603.18510/) (2026)
- [MS2Mesh-XR: Multi-modal Sketch-to-Mesh Generation in XR Environments](https://mlsanity.com/paper/2412.09008/) (2024)
- [Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning](https://mlsanity.com/paper/2605.29661/) (2026)
- [CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation](https://mlsanity.com/paper/2607.16577/) (2026)
- [Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation](https://mlsanity.com/paper/2607.19765/) (2026)
- [LEGO: Leveled Language Gaussian Splatting](https://mlsanity.com/paper/2608.10057/) (2026)
- [Every View Counts: View-Consistent Panoptic Quality for Multi-view Panoptic Segmentation](https://mlsanity.com/paper/2610.05911/) (2026)

## Abstract (arXiv)

Panoptic lifting is an effective technique to address the 3D panoptic segmentation task by unprojecting 2D panoptic segmentations from multi-views to 3D scene. However, the quality of its results largely depends on the 2D segmentations, which could be noisy and error-prone, so its performance often drops significantly for complex scenes. In this work, we design a new pipeline coined PCF-Lift based on our Probabilis-tic Contrastive Fusion (PCF) to learn and embed probabilistic features throughout our pipeline to actively consider inaccurate segmentations and inconsistent instance IDs. Technical-wise, we first model the probabilistic feature embeddings through multivariate Gaussian distributions. To fuse the probabilistic features, we incorporate the probability product kernel into the contrastive loss formulation and design a cross-view constraint to enhance the feature consistency across different views. For the inference, we introduce a new probabilistic clustering method to effectively associate prototype features with the underlying 3D object instances for the generation of consistent panoptic segmentation results. Further, we provide a theoretical analysis to justify the superiority of the proposed probabilistic solution. By conducting extensive experiments, our PCF-lift not only significantly outperforms the state-of-the-art methods on widely used benchmarks including the ScanNet dataset and the challenging Messy Room dataset (4.4% improvement of scene-level PQ), but also demonstrates strong robustness when incorporating various 2D segmentation models or different levels of hand-crafted noise.