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

In recent years, Denoising Diffusion Probabilistic Models (DDPMs) havedemonstrated exceptional performance in various 2D generative tasks. Followingthis success, DDPMs have been extended to 3D shape generation, surpassingprevious methodologies in this domain. While many of these models areunconditional, some have explored the potential of using guidance fromdifferent modalities. In particular, image guidance for 3D generation has beenexplored through the utilization of CLIP embeddings. However, these embeddingsare designed to align images and text, and do not necessarily capture thespecific details needed for shape generation. To address this limitation andenhance image-guided 3D DDPMs with augmented 3D understanding, we introduceCISP (Contrastive Image-Shape Pre-training), obtaining a well-structuredimage-shape joint embedding space. Building upon CISP, we then introduce IC3D,a DDPM that harnesses CISP's guidance for 3D shape generation from single-viewimages. This generative diffusion model outperforms existing benchmarks in bothquality and diversity of generated 3D shapes. Moreover, despite IC3D'sgenerative nature, its generated shapes are preferred by human evaluators overa competitive single-view 3D reconstruction model. These properties contributeto a coherent embedding space, enabling latent interpolation and conditionedgeneration also from out-of-distribution images. We find IC3D able to generatecoherent and diverse completions also when presented with occluded views,rendering it applicable in controlled real-world scenarios.

IC3D: Image-Conditioned 3D Diffusion for Shape Generation