# Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

arXiv: https://arxiv.org/abs/2306.04633 · HTML: https://mlsanity.com/paper/2306.04633/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 67 references that are in the map.
- First posted on arXiv 7 Jun 2023.

## Builds on (most cited first, 30 of 52)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [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)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [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)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [On Mutual Information Maximization for Representation Learning](https://mlsanity.com/paper/1907.13625/) (2019)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [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)

## Built on by (most cited first, 30 of 64)

- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [GARField: Group Anything with Radiance Fields](https://mlsanity.com/paper/2401.09419/) (2024)
- [Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting](https://mlsanity.com/paper/2403.15624/) (2024)
- [OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning](https://mlsanity.com/paper/2311.11666/) (2023)
- [PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models](https://mlsanity.com/paper/2412.18608/) (2024)
- [EgoLifter: Open-world 3D Segmentation for Egocentric Perception](https://mlsanity.com/paper/2403.18118/) (2024)
- [SAM-guided Graph Cut for 3D Instance Segmentation](https://mlsanity.com/paper/2312.08372/) (2023)
- [N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields](https://mlsanity.com/paper/2403.10997/) (2024)
- [AutoPartGen: Autogressive 3D Part Generation and Discovery](https://mlsanity.com/paper/2507.13346/) (2025)
- [Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting](https://mlsanity.com/paper/2503.14029/) (2025)
- [Contrastive Gaussian Clustering: Weakly Supervised 3D Scene Segmentation](https://mlsanity.com/paper/2404.12784/) (2024)
- [SANeRF-HQ: Segment Anything for NeRF in High Quality](https://mlsanity.com/paper/2312.01531/) (2023)
- [PanSt3R: Multi-view Consistent Panoptic Segmentation](https://mlsanity.com/paper/2506.21348/) (2025)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [Panoptic Vision-Language Feature Fields](https://mlsanity.com/paper/2309.05448/) (2023)
- [PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting](https://mlsanity.com/paper/2410.17505/) (2024)
- [LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging](https://mlsanity.com/paper/2512.04939/) (2025)
- [PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion](https://mlsanity.com/paper/2410.10659/) (2024)
- [Tackling View-Dependent Semantics in 3D Language Gaussian Splatting](https://mlsanity.com/paper/2505.24746/) (2025)
- [SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images](https://mlsanity.com/paper/2505.23044/) (2025)
- [Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing](https://mlsanity.com/paper/2508.03227/) (2025)
- [SAMa: Material-aware 3D Selection and Segmentation](https://mlsanity.com/paper/2411.19322/) (2024)
- [Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields](https://mlsanity.com/paper/2501.19084/) (2025)
- [Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review](https://mlsanity.com/paper/2402.11141/) (2024)
- [PE3R: Perception-Efficient 3D Reconstruction](https://mlsanity.com/paper/2503.07507/) (2025)
- [COS3D: Collaborative Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2510.20238/) (2025)
- [TRASE: Tracking-free 4D Segmentation and Editing](https://mlsanity.com/paper/2411.19290/) (2024)
- [Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field](https://mlsanity.com/paper/2502.16303/) (2025)
- [PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction](https://mlsanity.com/paper/2407.01349/) (2024)
- [Planar Gaussian Splatting](https://mlsanity.com/paper/2412.01931/) (2024)

## Abstract (arXiv)

Instance segmentation in 3D is a challenging task due to the lack of large-scale annotated datasets. In this paper, we show that this task can be addressed effectively by leveraging instead 2D pre-trained models for instance segmentation. We propose a novel approach to lift 2D segments to 3D and fuse them by means of a neural field representation, which encourages multi-view consistency across frames. The core of our approach is a slow-fast clustering objective function, which is scalable and well-suited for scenes with a large number of objects. Unlike previous approaches, our method does not require an upper bound on the number of objects or object tracking across frames. To demonstrate the scalability of the slow-fast clustering, we create a new semi-realistic dataset called the Messy Rooms dataset, which features scenes with up to 500 objects per scene. Our approach outperforms the state-of-the-art on challenging scenes from the ScanNet, Hypersim, and Replica datasets, as well as on our newly created Messy Rooms dataset, demonstrating the effectiveness and scalability of our slow-fast clustering method.