# Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenization

arXiv: https://arxiv.org/abs/2505.18819 · HTML: https://mlsanity.com/paper/2505.18819/

## Key facts

- Cited by 1 papers in the map (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 54 of its 79 references that are in the map.
- First posted on arXiv 24 May 2025.

## 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 54)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [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)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [A Simple Framework for Open-Vocabulary Segmentation and Detection](https://mlsanity.com/paper/2303.08131/) (2023)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)

## Built on by (most cited first, 1 of 1)

- [Masked Clustering Prediction for Unsupervised Point Cloud Pre-training](https://mlsanity.com/paper/2508.08910/) (2025)

## Abstract (arXiv)

Vision-language models, such as CLIP, encode rich semantic knowledge through large-scale image-text pretraining. Reusing these models for 3D understanding is highly desirable, because 3D-text pairs and dense point-level annotations are far scarcer and more difficult to obtain than their 2D counterparts. However, CLIP is trained on regular 2D image patches, whereas point clouds are unordered, sparse, and irregular. The primary challenge lies in constructing 3D token sequences whose geometry, position, and local relations can be interpreted by a frozen, pretrained vision transformer. Moreover, coordinate-scale variations across heterogeneous 3D domains make unified training particularly challenging. To bridge these gaps, we propose a parameter-efficient framework that learns a scale-normalized 3D tokenizer, enabling the CLIP visual encoder to be reused for point-cloud understanding. Our tokenizer, named UTok3D, estimates an input-adaptive geometric scale to calibrate sparse voxelization, coordinate normalization, token-center computation, and 3D positional encoding, and serializes the resulting tokens by Hilbert ordering. This shared geometric convention makes joint training feasible across point clouds with substantially different metric scales, including object-level shapes, indoor scenes, and outdoor LiDAR scans. The tokenizer is trained without 3D annotations through self-supervised cross-modal distillation from foundation-model features extracted from multi-view images, combining local superpoint alignment with the proposed Sinkhorn Ranked Contrastive distillation. Experiments on ShapeNetPart, ScanNetV2, S3DIS, SemanticKITTI, and nuScenes show that, when equipped with a scale-consistent and CLIP-interpretable token interface, a frozen CLIP visual backbone can be effectively reused for annotation-free 3D segmentation.