# XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation

arXiv: https://arxiv.org/abs/2411.13243 · HTML: https://mlsanity.com/paper/2411.13243/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 51 references that are in the map.
- First posted on arXiv 20 Nov 2024.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 15 of 15)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [Weakly Supervised 3D Open-vocabulary Segmentation](https://mlsanity.com/paper/2305.14093/) (2023)
- [Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models](https://mlsanity.com/paper/2207.11514/) (2022)
- [RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding](https://mlsanity.com/paper/2304.00962/) (2023)
- [Diffusion Models for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2306.09316/) (2023)
- [Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models](https://mlsanity.com/paper/2210.15138/) (2022)
- [UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature Representation](https://mlsanity.com/paper/2401.11395/) (2024)
- [TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2304.07547/) (2023)
- [3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation](https://mlsanity.com/paper/2401.02402/) (2024)

## Built on by (most cited first, 5 of 5)

- [PGOV3D: Open-Vocabulary 3D Semantic Segmentation with Partial-to-Global Curriculum](https://mlsanity.com/paper/2506.23607/) (2025)
- [Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model](https://mlsanity.com/paper/2509.07825/) (2025)
- [GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2510.02186/) (2025)
- [GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation](https://mlsanity.com/paper/2603.26260/) (2026)
- [Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applications](https://mlsanity.com/paper/2607.00978/) (2026)

## Abstract (arXiv)

Existing methodologies in open vocabulary 3D semantic segmentation primarily concentrate on establishing a unified feature space encompassing 3D, 2D, and textual modalities. Nevertheless, traditional techniques such as global feature alignment or vision-language model distillation tend to impose only approximate correspondence, struggling notably with delineating fine-grained segmentation boundaries. To address this gap, we propose a more meticulous mask-level alignment between 3D features and the 2D-text embedding space through a cross-modal mask reasoning framework, XMask3D. In our approach, we developed a mask generator based on the denoising UNet from a pre-trained diffusion model, leveraging its capability for precise textual control over dense pixel representations and enhancing the open-world adaptability of the generated masks. We further integrate 3D global features as implicit conditions into the pre-trained 2D denoising UNet, enabling the generation of segmentation masks with additional 3D geometry awareness. Subsequently, the generated 2D masks are employed to align mask-level 3D representations with the vision-language feature space, thereby augmenting the open vocabulary capability of 3D geometry embeddings. Finally, we fuse complementary 2D and 3D mask features, resulting in competitive performance across multiple benchmarks for 3D open vocabulary semantic segmentation. Code is available at https://github.com/wangzy22/XMask3D.