English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large pre-trained models have had a significant impact on computer vision byenabling multi-modal learning, where the CLIP model has achieved impressiveresults in image classification, object detection, and semantic segmentation.However, the model's performance on 3D point cloud processing tasks is limiteddue to the domain gap between depth maps from 3D projection and training imagesof CLIP. This paper proposes DiffCLIP, a new pre-training framework thatincorporates stable diffusion with ControlNet to minimize the domain gap in thevisual branch. Additionally, a style-prompt generation module is introduced forfew-shot tasks in the textual branch. Extensive experiments on the ModelNet10,ModelNet40, and ScanObjectNN datasets show that DiffCLIP has strong abilitiesfor 3D understanding. By using stable diffusion and style-prompt generation,DiffCLIP achieves an accuracy of 43.2\% for zero-shot classification on OBJ\_BGof ScanObjectNN, which is state-of-the-art performance, and an accuracy of80.6\% for zero-shot classification on ModelNet10, which is comparable tostate-of-the-art performance.

DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification