Since the past few months, I have been quite fascinated with Rendering in Computer Graphics.
Rendering or image synthesis is the process of generating a photorealistic or non-photorealistic image from a 2D or 3D model by means of a computer program.
However, mostly until now, we have been focused on forward rendering. Inverse rendering aims to estimate physical attributes of a scene, e.g., reflectance, geometry, and lighting, from image(s). Renderers currently are not designed to solve this issue, and thus, we need a separate set of renderers known as “DIfferentiable Renderers” that can retain the derivatives to determine the attributes of a scene.
Several form of differentiable renderers exist such as,
- Ray Marching
- Point-Based Techniques
- Single Shaded Surface