PSDR-Room: Single Photo to Scene using Differentiable Rendering
This addresses the time-consuming and skill-intensive task of 3D scene staging for artists and designers, though it is incremental as it builds on existing differentiable rendering and scene understanding methods.
The paper tackles the problem of reconstructing and editing 3D room scenes from a single photo by optimizing lighting, object poses, and materials to match the target image, using minimal user input and demonstrating editability on real photographs.
A 3D digital scene contains many components: lights, materials and geometries, interacting to reach the desired appearance. Staging such a scene is time-consuming and requires both artistic and technical skills. In this work, we propose PSDR-Room, a system allowing to optimize lighting as well as the pose and materials of individual objects to match a target image of a room scene, with minimal user input. To this end, we leverage a recent path-space differentiable rendering approach that provides unbiased gradients of the rendering with respect to geometry, lighting, and procedural materials, allowing us to optimize all of these components using gradient descent to visually match the input photo appearance. We use recent single-image scene understanding methods to initialize the optimization and search for appropriate 3D models and materials. We evaluate our method on real photographs of indoor scenes and demonstrate the editability of the resulting scene components.