arXiv:2512.15632v1 Announce Type: new 
Abstract: Accurate environment maps are a key component for rendering photorealistic outdoor scenes with coherent illumination. They enable captivating visual arts, immersive virtual reality, and a wide range of engineering and scientific applications. Recent works have extended sky-models to be more comprehensive and inclusive of cloud formations but, as we demonstrate, existing methods fall short in faithfully recreating natural skies. Though in recent years the visual quality of DNN-generated High Dynamic Range Imagery (HDRI) has greatly improved, the environment maps generated by DNN sky-models do not re-light scenes with the same tones, shadows, and illumination as physically captured HDR imagery. In this work, we demonstrate progress in HDR literature to be tangential to sky-modelling as current works cannot support both photorealism and the 22 f-stops required for the Full Dynamic Range (FDR) of outdoor illumination. We achieve this by proposing AllSky, a flexible all-weather sky-model learned directly from physically captured HDRI which we leverage to study the input modalities, tonemapping, conditioning, and evaluation of sky-models. Per user-controlled positioning of the sun and cloud formations, AllSky expands on current functionality by allowing for intuitive user control over environment maps and achieves state-of-the-art sky-model performance. Through our proposed evaluation, we demonstrate existing DNN sky-models are not interchangeable with physically captured HDRI or parametric sky-models, with current limitations being prohibitive of scalability and accurate illumination in downstream applications

تسلط دراسة جديدة بعنوان 'Towards Physically-Based Sky-Modeling For Image Based Lighting' الضوء على قيود تقنيات نمذجة السماء الحالية في إعادة إنشاء السماء الطبيعية بدقة للرسم الفوتوغرافي الواقعي. تشير الأبحاث إلى أنه على الرغم من أن التطورات الأخيرة في الصور عالية الديناميكية (HDRI) التي تم إنشاؤها بواسطة الشبكات العصبية العميقة (DNN) قد حسنت الجودة البصرية، إلا أنها لا تزال تفشل في مطابقة خصائص الإضاءة للصور HDR الملتقطة بشكل فعلي.

Un nuevo estudio titulado 'Towards Physically-Based Sky-Modeling For Image Based Lighting' destaca las limitaciones de las técnicas actuales de modelado del cielo para recrear con precisión cielos naturales en renderizados fotorrealistas. La investigación indica que, aunque los avances recientes en imágenes de alto rango dinámico (HDRI) generadas por DNN han mejorado la calidad visual, aún no logran igualar las características de iluminación de las imágenes HDR capturadas físicamente.

Une nouvelle étude intitulée 'Towards Physically-Based Sky-Modeling For Image Based Lighting' met en lumière les limites des techniques de modélisation du ciel actuelles dans la recréation précise des ciels naturels pour le rendu photoréaliste. La recherche indique que, bien que les avancées récentes dans l'imagerie à grande gamme dynamique générée par DNN aient amélioré la qualité visuelle, elles ne parviennent toujours pas à égaler les caractéristiques d'illumination de l'imagerie HDR capturée physiquement.

A new study titled 'Towards Physically-Based Sky-Modeling For Image Based Lighting' highlights the limitations of current sky-modeling techniques in accurately recreating natural skies for photorealistic rendering. The research indicates that while recent advancements in DNN-generated High Dynamic Range Imagery (HDRI) have improved visual quality, they still fail to match the illumination characteristics of physically captured HDR imagery.

Towards Physically-Based Sky-Modeling For Image Based Lighting

Was this article worth reading? Share it

4o Image Gen

Uwear

FLUX AI ART

HomeStage

Novaheadshot

OneSky Localization Agent

Ready to build your own newsroom?