# Language-Assisted 3D Scene Understanding

arXiv: https://arxiv.org/abs/2312.11451 · HTML: https://mlsanity.com/paper/2312.11451/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 55 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (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)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?](https://mlsanity.com/paper/2212.08320/) (2022)
- [Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding](https://mlsanity.com/paper/2304.06906/) (2023)
- [CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP](https://mlsanity.com/paper/2303.04748/) (2023)
- [P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting](https://mlsanity.com/paper/2208.02812/) (2022)
- [EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder](https://mlsanity.com/paper/2212.04098/) (2022)
- [3D Point Cloud Pre-training with Knowledge Distillation from 2D Images](https://mlsanity.com/paper/2212.08974/) (2022)
- [Point Clouds Are Specialized Images: A Knowledge Transfer Approach for 3D Understanding](https://mlsanity.com/paper/2307.15569/) (2023)

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

- [InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception](https://mlsanity.com/paper/2411.19235/) (2024)
- [A Unified Framework for 3D Scene Understanding](https://mlsanity.com/paper/2407.03263/) (2024)
- [BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis](https://mlsanity.com/paper/2503.12539/) (2025)
- [SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering](https://mlsanity.com/paper/2603.29437/) (2026)
- [FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding](https://mlsanity.com/paper/2506.13629/) (2025)
- [Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction](https://mlsanity.com/paper/2605.06270/) (2026)

## Abstract (arXiv)

The scale and quality of point cloud datasets constrain the advancement of point cloud learning. Recently, with the development of multi-modal learning, the incorporation of domain-agnostic prior knowledge from other modalities, such as images and text, to assist in point cloud feature learning has been considered a promising avenue. Existing methods have demonstrated the effectiveness of multi-modal contrastive training and feature distillation on point clouds. However, challenges remain, including the requirement for paired triplet data, redundancy and ambiguity in supervised features, and the disruption of the original priors. In this paper, we propose a language-assisted approach to point cloud feature learning (LAST-PCL), enriching semantic concepts through LLMs-based text enrichment. We achieve de-redundancy and feature dimensionality reduction without compromising textual priors by statistical-based and training-free significant feature selection. Furthermore, we also delve into an in-depth analysis of the impact of text contrastive training on the point cloud. Extensive experiments validate that the proposed method learns semantically meaningful point cloud features and achieves state-of-the-art or comparable performance in 3D semantic segmentation, 3D object detection, and 3D scene classification tasks.