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 image diffusion models enable novel view synthesis with high qualityand excellent zero-shot capability. However, such models based onimage-to-image translation have no guarantee of view consistency, limiting theperformance for downstream tasks like 3D reconstruction and image-to-3Dgeneration. To empower consistency, we propose Consistent123 to synthesizenovel views simultaneously by incorporating additional cross-view attentionlayers and the shared self-attention mechanism. The proposed attentionmechanism improves the interaction across all synthesized views, as well as thealignment between the condition view and novel views. In the sampling stage,such architecture supports simultaneously generating an arbitrary number ofviews while training at a fixed length. We also introduce a progressiveclassifier-free guidance strategy to achieve the trade-off between texture andgeometry for synthesized object views. Qualitative and quantitative experimentsshow that Consistent123 outperforms baselines in view consistency by a largemargin. Furthermore, we demonstrate a significant improvement of Consistent123on varying downstream tasks, showing its great potential in the 3D generationfield. The project page is available at consistent-123.github.io.

Consistent123: Improve Consistency for One Image to 3D Object Synthesis