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 propose a deep inverse rendering framework for indoor scenes. From asingle RGB image of an arbitrary indoor scene, we create a complete scenereconstruction, estimating shape, spatially-varying lighting, andspatially-varying, non-Lambertian surface reflectance. To train this network,we augment the SUNCG indoor scene dataset with real-world materials and renderthem with a fast, high-quality, physically-based GPU renderer to create alarge-scale, photorealistic indoor dataset. Our inverse rendering networkincorporates physical insights -- including a spatially-varying sphericalGaussian lighting representation, a differentiable rendering layer to modelscene appearance, a cascade structure to iteratively refine the predictions anda bilateral solver for refinement -- allowing us to jointly reason about shape,lighting, and reflectance. Experiments show that our framework outperformsprevious methods for estimating individual scene components, which also enablesvarious novel applications for augmented reality, such as photorealistic objectinsertion and material editing. Code and data will be made publicly available.

Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image