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

Reconstructing the 3D shape of an object from a single RGB image is along-standing and highly challenging problem in computer vision. In this paper,we propose a novel method for single-image 3D reconstruction which generates asparse point cloud via a conditional denoising diffusion process. Our methodtakes as input a single RGB image along with its camera pose and graduallydenoises a set of 3D points, whose positions are initially sampled randomlyfrom a three-dimensional Gaussian distribution, into the shape of an object.The key to our method is a geometrically-consistent conditioning process whichwe call projection conditioning: at each step in the diffusion process, weproject local image features onto the partially-denoised point cloud from thegiven camera pose. This projection conditioning process enables us to generatehigh-resolution sparse geometries that are well-aligned with the input image,and can additionally be used to predict point colors after shapereconstruction. Moreover, due to the probabilistic nature of the diffusionprocess, our method is naturally capable of generating multiple differentshapes consistent with a single input image. In contrast to prior work, ourapproach not only performs well on synthetic benchmarks, but also gives largequalitative improvements on complex real-world data.

$PC^2$: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction