OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding

by   Minghua Liu, et al.

We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but with a specific focus on scaling up 3D representations to enable open-world 3D shape understanding. To achieve this, we scale up training data by ensembling multiple 3D datasets and propose several strategies to automatically filter and enrich noisy text descriptions. We also explore and compare strategies for scaling 3D backbone networks and introduce a novel hard negative mining module for more efficient training. We evaluate OpenShape on zero-shot 3D classification benchmarks and demonstrate its superior capabilities for open-world recognition. Specifically, OpenShape achieves a zero-shot accuracy of 46.8 10 ModelNet40, outperforming previous zero-shot baseline methods by 20 performing on par with some fully-supervised methods. Furthermore, we show that our learned embeddings encode a wide range of visual and semantic concepts (e.g., subcategories, color, shape, style) and facilitate fine-grained text-3D and image-3D interactions. Due to their alignment with CLIP embeddings, our learned shape representations can also be integrated with off-the-shelf CLIP-based models for various applications, such as point cloud captioning and point cloud-conditioned image generation.


page 2

page 4

page 5

page 8

page 9


See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data

Zero-shot point cloud segmentation aims to make deep models capable of r...

PointCLIP V2: Adapting CLIP for Powerful 3D Open-world Learning

Contrastive Language-Image Pre-training (CLIP) has shown promising open-...

CLIP^2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data

Contrastive Language-Image Pre-training, benefiting from large-scale unl...

CoBIT: A Contrastive Bi-directional Image-Text Generation Model

The field of vision and language has witnessed a proliferation of pre-tr...

Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation

In recent years, 3D representation learning has turned to 2D vision-lang...

Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning

Recently, multi-modal vision-language foundation models have gained sign...

PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models

Generalizable 3D part segmentation is important but challenging in visio...

Please sign up or login with your details

Forgot password? Click here to reset