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

We present iFusion, a novel 3D object reconstruction framework that requiresonly two views with unknown camera poses. While single-view reconstructionyields visually appealing results, it can deviate significantly from the actualobject, especially on unseen sides. Additional views improve reconstructionfidelity but necessitate known camera poses. However, assuming the availabilityof pose may be unrealistic, and existing pose estimators fail in sparse viewscenarios. To address this, we harness a pre-trained novel view synthesisdiffusion model, which embeds implicit knowledge about the geometry andappearance of diverse objects. Our strategy unfolds in three steps: (1) Weinvert the diffusion model for camera pose estimation instead of synthesizingnovel views. (2) The diffusion model is fine-tuned using provided views andestimated poses, turned into a novel view synthesizer tailored for the targetobject. (3) Leveraging registered views and the fine-tuned diffusion model, wereconstruct the 3D object. Experiments demonstrate strong performance in bothpose estimation and novel view synthesis. Moreover, iFusion seamlesslyintegrates with various reconstruction methods and enhances them.

iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views