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

Indoor scenes exhibit significant appearance variations due to myriadinteractions between arbitrarily diverse object shapes, spatially-changingmaterials, and complex lighting. Shadows, highlights, and inter-reflectionscaused by visible and invisible light sources require reasoning aboutlong-range interactions for inverse rendering, which seeks to recover thecomponents of image formation, namely, shape, material, and lighting. In thiswork, our intuition is that the long-range attention learned by transformerarchitectures is ideally suited to solve longstanding challenges insingle-image inverse rendering. We demonstrate with a specific instantiation ofa dense vision transformer, IRISformer, that excels at both single-task andmulti-task reasoning required for inverse rendering. Specifically, we propose atransformer architecture to simultaneously estimate depths, normals,spatially-varying albedo, roughness and lighting from a single image of anindoor scene. Our extensive evaluations on benchmark datasets demonstratestate-of-the-art results on each of the above tasks, enabling applications likeobject insertion and material editing in a single unconstrained real image,with greater photorealism than prior works. Code and data are publicly releasedat https://github.com/ViLab-UCSD/IRISformer.

IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes