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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Estimating 3D articulated shapes like animal bodies from monocular images isinherently challenging due to the ambiguities of camera viewpoint, pose,texture, lighting, etc. We propose ARTIC3D, a self-supervised framework toreconstruct per-instance 3D shapes from a sparse image collection in-the-wild.Specifically, ARTIC3D is built upon a skeleton-based surface representation andis further guided by 2D diffusion priors from Stable Diffusion. First, weenhance the input images with occlusions/truncation via 2D diffusion to obtaincleaner mask estimates and semantic features. Second, we performdiffusion-guided 3D optimization to estimate shape and texture that are ofhigh-fidelity and faithful to input images. We also propose a novel techniqueto calculate more stable image-level gradients via diffusion models compared toexisting alternatives. Finally, we produce realistic animations by fine-tuningthe rendered shape and texture under rigid part transformations. Extensiveevaluations on multiple existing datasets as well as newly introduced noisy webimage collections with occlusions and truncation demonstrate that ARTIC3Doutputs are more robust to noisy images, higher quality in terms of shape andtexture details, and more realistic when animated. Project page:https://chhankyao.github.io/artic3d/

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections