Appearance Editing with Free-viewpoint Neural Rendering
This enables direct control over scene appearance for applications like virtual reality or film production, though it builds incrementally on existing neural rendering techniques.
The paper tackles the problem of simultaneously synthesizing novel views and editing the appearance of a scene from multi-view images, achieving results comparable to state-of-the-art view synthesis methods.
We present a neural rendering framework for simultaneous view synthesis and appearance editing of a scene from multi-view images captured under known environment illumination. Existing approaches either achieve view synthesis alone or view synthesis along with relighting, without direct control over the scene's appearance. Our approach explicitly disentangles the appearance and learns a lighting representation that is independent of it. Specifically, we independently estimate the BRDF and use it to learn a lighting-only representation of the scene. Such disentanglement allows our approach to generalize to arbitrary changes in appearance while performing view synthesis. We show results of editing the appearance of a real scene, demonstrating that our approach produces plausible appearance editing. The performance of our view synthesis approach is demonstrated to be at par with state-of-the-art approaches on both real and synthetic data.