# Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

arXiv: https://arxiv.org/abs/2407.13642 · HTML: https://mlsanity.com/paper/2407.13642/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 81 of its 91 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 30 of 81)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [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)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [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)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)

## Built on by (most cited first, 12 of 12)

- [SAS: Segment Any 3D Scene with Integrated 2D Priors](https://mlsanity.com/paper/2503.08512/) (2025)
- [PGOV3D: Open-Vocabulary 3D Semantic Segmentation with Partial-to-Global Curriculum](https://mlsanity.com/paper/2506.23607/) (2025)
- [CitySeg: A 3D Open Vocabulary Semantic Segmentation Foundation Model in City-scale Scenarios](https://mlsanity.com/paper/2508.09470/) (2025)
- [Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model](https://mlsanity.com/paper/2509.07825/) (2025)
- [GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation](https://mlsanity.com/paper/2603.26260/) (2026)
- [Unlocking Diffusion Hierarchies: Adaptive Timestep Selection for Zero-Shot Segmentation](https://mlsanity.com/paper/2606.15590/) (2026)
- [Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applications](https://mlsanity.com/paper/2607.00978/) (2026)
- [Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning](https://mlsanity.com/paper/2608.15869/) (2026)
- [Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2506.22817/) (2025)
- [OpenHuman4D: Open-Vocabulary 4D Human Parsing](https://mlsanity.com/paper/2507.09880/) (2025)
- [ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings](https://mlsanity.com/paper/2605.08925/) (2026)
- [Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training](https://mlsanity.com/paper/2608.19973/) (2026)

## Abstract (arXiv)

In this paper, we investigate the use of diffusion models which are pre-trained on large-scale image-caption pairs for open-vocabulary 3D semantic understanding. We propose a novel method, namely Diff2Scene, which leverages frozen representations from text-image generative models, along with salient-aware and geometric-aware masks, for open-vocabulary 3D semantic segmentation and visual grounding tasks. Diff2Scene gets rid of any labeled 3D data and effectively identifies objects, appearances, materials, locations and their compositions in 3D scenes. We show that it outperforms competitive baselines and achieves significant improvements over state-of-the-art methods. In particular, Diff2Scene improves the state-of-the-art method on ScanNet200 by 12%.