# Cross-Attentive Multiview Fusion of Vision-Language Embeddings

arXiv: https://arxiv.org/abs/2604.12551 · HTML: https://mlsanity.com/paper/2604.12551/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 46 of its 49 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 46)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations](https://mlsanity.com/paper/2111.13152/) (2021)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023)
- [MUSt3R: Multi-view Network for Stereo 3D Reconstruction](https://mlsanity.com/paper/2503.01661/) (2025)
- [Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance](https://mlsanity.com/paper/2312.10671/) (2023)
- [ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2408.04883/) (2024)
- [SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos](https://mlsanity.com/paper/2412.09401/) (2024)
- [Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships](https://mlsanity.com/paper/2402.12259/) (2024)

## Abstract (arXiv)

Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and average 2D descriptors across views, or heuristically select a single representative one, often resulting in suboptimal 3D representations. In this work, we introduce a novel multiview transformer architecture that cross-attends across vision-language descriptors from multiple viewpoints and fuses them into a unified per-3D-instance embedding. As a second contribution, we leverage multiview consistency as a self-supervision signal for this fusion, which significantly improves performance when added to a standard supervised target-class loss. Our Cross-Attentive Multiview Fusion, which we denote with its acronym CAMFusion, not only consistently outperforms naive averaging or single-view descriptor selection, but also achieves state-of-the-art results on 3D semantic and instance classification benchmarks, including zero-shot evaluations on out-of-domain datasets.