# GS-CLIP: Gaussian Splatting for Contrastive Language-Image-3D Pretraining from Real-World Data

arXiv: https://arxiv.org/abs/2402.06198 · HTML: https://mlsanity.com/paper/2402.06198/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts](https://mlsanity.com/paper/2111.08276/) (2021)
- [ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding](https://mlsanity.com/paper/2305.08275/) (2023)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning](https://mlsanity.com/paper/2104.03135/) (2021)
- [CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training](https://mlsanity.com/paper/2210.01055/) (2022)
- [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.11183/) (2022)
- [Open Vocabulary Object Detection with Pseudo Bounding-Box Labels](https://mlsanity.com/paper/2111.09452/) (2021)
- [CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data](https://mlsanity.com/paper/2303.12417/) (2023)

## Built on by (most cited first, 2 of 2)

- [Multimodal Alignment and Fusion: A Survey](https://mlsanity.com/paper/2411.17040/) (2024)
- [Bridging the Modality Gap in Roadside LiDAR: A Training-Free Vision-Language Model Framework for Vehicle Classification](https://mlsanity.com/paper/2602.09425/) (2026)

## Abstract (arXiv)

3D Shape represented as point cloud has achieve advancements in multimodal pre-training to align image and language descriptions, which is curial to object identification, classification, and retrieval. However, the discrete representations of point cloud lost the object's surface shape information and creates a gap between rendering results and 2D correspondences. To address this problem, we propose GS-CLIP for the first attempt to introduce 3DGS (3D Gaussian Splatting) into multimodal pre-training to enhance 3D representation. GS-CLIP leverages a pre-trained vision-language model for a learned common visual and textual space on massive real world image-text pairs and then learns a 3D Encoder for aligning 3DGS optimized per object. Additionally, a novel Gaussian-Aware Fusion is proposed to extract and fuse global explicit feature. As a general framework for language-image-3D pre-training, GS-CLIP is agnostic to 3D backbone networks. Experiments on challenging shows that GS-CLIP significantly improves the state-of-the-art, outperforming the previously best results.