five

Render Lighting Dataset: A Collection of Rendered Images with Varied Lighting Conditions using Blender Render Engines

收藏
NIAID Data Ecosystem2026-05-01 收录
下载链接:
https://data.mendeley.com/datasets/c49hdpxvyw
下载链接
链接失效反馈
官方服务:
资源简介:
This dataset consists of a wide range of 3D rendered images that showcase various 3D primitive shapes under different lighting conditions. These images have been created using Blender's Cycles and Eevee Render Engines, and there are a total of 63,648 RGB images available for researchers to use in their analysis and experimentation. The Blender source file has also been provided for easier reproducibility. Each rendered image in the dataset features primitive shapes such as Cube, Cone, Cylinder (Hollow), Icosphere, Sphere (Subdivided Cube), and Torus, with additional geometry to enhance texture mapping and UV unwrapping. The dataset offers six different lighting setups that include Area Light, Spot Light, Point Light, Tri Light (built-in addon), HDRI (Sunlight), and HDRI (Overcast). Additionally, each rendering has been adjusted using Blender's Color Management panel, with View Transform and Look options tailored to four distinct settings: AGX (None), AGX (Punchy), Filmic (None), and Filmic (High Contrast). With 17 different camera angles capturing each rendered scene, researchers can explore the interplay between lighting, materials, and geometry from various perspectives. The dataset also includes 13 distinct materials, such as Rough Concrete, Fabric Denim, Fabric Leather, Clear Glass, Brushed Steel, Corroded Steel, Polished Gold, Gold Paint, Glossy Plastic, Coastal Sand, Cracked Mud, Terracotta, and Plywood. This diverse range of materials allows researchers to study material properties and visual aesthetics in great detail. The Render Lighting Dataset is a valuable resource for advancing research in computer graphics, machine learning, and other related fields. Whether investigating rendering algorithms, studying material interactions, or developing computer vision models, this dataset provides a robust foundation for exploration and analysis.
创建时间:
2024-02-26
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作