Virtual Home Staging
Our virtual staging research at Illumination and Imaging Laboratory (ILIM) within CMU Robotics Institute focuses on understanding indoor scenes through 2D images. Using physics-based and data-driven approaches, we aim to manipulate the visual characteristics of indoor environments. Our approach allows for precise scene editing and relighting of indoor appearances, enabling a wide range of applications, from virtual home staging to physical environment simulations. Through this work, we seek to bridge the gap between visual perception and computational models, providing virtual indoor scenes that are both visually compelling and physically accurate.
Indoor Appearance Analysis
"Semantically Supervised Appearance Decomposition for Virtual Staging from a Single Panorama"
Tiancheng Zhi, Bowei Chen, Ivaylo Boyadzhiev, Sing Bing Kang, Martial Hebert, and Srinivasa G. Narasimhan
ACM Transactions on Graphics (SIGGRAPH), 2022
[Project Webpage] [Paper (130 MB)] [Compressed Paper (7 MB)] [Supp] [Code]
A single panorama of an empty indoor environment (top left) is decomposed into four appearance components on the floor and walls: specular and direct sunlight (bottom left), diffuse (not shown) and diffuse ambient without direct sunlight (bottom right). Although the decomposition is not perfect (e.g. power sockets are removed in the bottom right), we demonstrate its effectiveness in enabling high quality virtual staging applications including furniture insertion∗(top right), changing flooring and sun direction. Multiple realistic effects are rendered, including shadows under the table, sunlight on the side table, sofa pillows, beanbag, dining table and chaise lounge, occlusion of specular reflection by the sofa and chair. The plant creates soft and hard shadows by blocking the skylight and the sunlight.
Indoor Scene Relighting
"Virtual home staging and relighting from a single panorama under natural illumination"
Guanzhou Ji, Azadeh O. Sawyer, and Srinivasa G. Narasimhan
Machine Vision and Applications 35, 98 (2024)
"Virtual home staging: Inverse rendering and editing an indoor panorama under natural illumination"
Guanzhou Ji, Azadeh O. Sawyer, and Srinivasa G. Narasimhan
International Symposium on Visual Computing, 2023
[Project Webpage] [Journal Paper] [Conference Paper] [Code]
Illustration of Our Rendering Approach: A real-world scene (left) is captured at 11:27AM(cloudy sky condition).Different furniture objects are removed from the existing room, and the empty scene is refurnished with new virtual furniture objects. A new panorama (right) is then virtually rendered with edited camera position, outdoor illumination at 01:00 PM (clear sky condition), scene textures, and electrical light.
Intricate Scenes Remodeling
"Kitchen Remodeling: Editing and Relighting Intricate Indoor Scenes from a Single Panorama"
Guanzhou Ji, Azadeh O. Sawyer, and Srinivasa G. Narasimhan
"Capturing, Editing, and Relighting Indoor Scenes from a Single Panorama"
Guanzhou Ji, 2025
An indoor panorama showcases a scene with kitchen and living spaces. The existing kitchen area is remodeled with a new dark gray background wall and a new set of cabinets and appliances. The gray-blue cabinets reflect the detailed scene on their surfaces, while the refrigerator with metal surfaces shows fewer reflective effects. For the living space, the existing furniture is removed, and the room is refurnished with a new set of furniture.
Image-Based Rendering
"IES25 Workshop: Omnidirectional HDR Photography"
Guanzhou Ji, Zining Cheng
Anaheim CA, August 21, 2025
This workshop teaches a technique for creating HDR panoramas of both indoor and outdoor spaces using multiple Low Dynamic Range (LDR) images taken on-site. Participants will gain hands-on experience in image processing, tone mapping, and generating high-quality HDR images. They will also learn how to use these HDR panoramas as realistic lighting sources for rendering and inserting virtual objects into real-world scenes.
Indoor Light and Heat Estimation
"Indoor Light and Heat Estimation from a Single Panorama"
Guanzhou Ji, Sriram Narayanan, Azadeh O. Sawyer, Srinivasa G. Narasimhan
An indoor panorama is captured under natural illumination, with a paired outdoor panorama providing real-time, spatially-varying light to the scene. We bridge the light transport with heat transport and implement transient heat simulation to compute indoor heat map displaying per-pixel temperature values.