PSDR-Room: Single Photo to Scene using Differentiable Rendering

TL;DR

PSDR-Room is a system that reconstructs and optimizes indoor scene components from a single photo using differentiable rendering, enabling realistic scene editing with minimal user input.

Contribution

It introduces a differentiable rendering-based approach for optimizing lighting, geometry, and materials of indoor scenes from a single image, with minimal user input.

Findings

Successfully reconstructs indoor scenes from single images.

Enables scene editing and customization.

Demonstrates effective optimization using gradient descent.

Abstract

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.