# MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding

arXiv: https://arxiv.org/abs/2511.22103 · HTML: https://mlsanity.com/paper/2511.22103/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 55 of its 73 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 30 of 55)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://mlsanity.com/paper/2401.15947/) (2024)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment](https://mlsanity.com/paper/2308.04352/) (2023)
- [Tutel: Adaptive Mixture-of-Experts at Scale](https://mlsanity.com/paper/2206.03382/) (2022)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection](https://mlsanity.com/paper/2004.12636/) (2020)
- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)

## Built on by (most cited first, 6 of 6)

- [Segment and Select: Vision-Language Segmentation in 3D Scenarios](https://mlsanity.com/paper/2606.10594/) (2026)
- [Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection](https://mlsanity.com/paper/2604.05405/) (2026)
- [LER-YOLO: Reliability-Aware Expert Routing for Misaligned RGB-Infrared UAV Detection](https://mlsanity.com/paper/2605.20667/) (2026)
- [Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation](https://mlsanity.com/paper/2606.25278/) (2026)
- [CMTFormer: Marrying Transformer with Hierarchical Information Interaction for RGB-Event Object Detection](https://mlsanity.com/paper/2606.29136/) (2026)
- [PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet](https://mlsanity.com/paper/2607.06097/) (2026)

## Abstract (arXiv)

Multi-modal 3D understanding is a fundamental task in computer vision. Previous multi-modal fusion methods typically employ a single, dense fusion network, struggling to handle the significant heterogeneity and complexity across modalities, leading to suboptimal performance. In this paper, we propose MoE3D, which integrates Mixture of Experts (MoE) into the multi-modal learning framework. The core is that we deploy a set of specialized "expert" networks, each adept at processing a specific modality or a mode of cross-modal interaction. Specifically, the MoE-based transformer is designed to better utilize the complementary information hidden in the visual features. Information aggregation module is put forward to further enhance the fusion performance. Top-1 gating is employed to make one expert process features with expert groups, ensuring high efficiency. We further propose a progressive pre-training strategy to better leverage the semantic and 2D prior, thus equipping the network with good initialization. Our MoE3D achieves competitive performance across four prevalent 3D understanding tasks. Notably, our MoE3D surpasses the top-performing counterpart by 6.1 mIoU on Multi3DRefer.