| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://senguptaumd.github.io/Neural-Inverse-Rendering/
x-github-request-id: 304E:2B0FD4:9034D6:A1BEDF:69529A79
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 15:12:57 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210038-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767021177.357757,VS0,VE200
vary: Accept-Encoding
x-fastly-request-id: 53a44387d43bfdc85218a84252a60ee5f1c4442c
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Mon, 21 Oct 2019 01:12:01 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"5dad05e1-2ea0"
expires: Mon, 29 Dec 2025 15:22:57 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 8AEA:21D6A4:9130B4:A2BB3C:69529A78
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 15:12:57 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210038-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767021178.572007,VS0,VE218
vary: Accept-Encoding
x-fastly-request-id: ed90c37fd7ddc4a45d0969e1b656d7abae112300
content-length: 3523
Neural Inverse Rendering
Neural Inverse Rendering of an Indoor Scene From a Single Image
Inverse rendering aims to estimate physical attributes of a scene, e.g., reflectance, geometry, and lighting, from image(s). Inverse rendering has been studied primarily for single objects or with methods that solve for only one of the scene attributes. We propose the first learning based approach that jointly estimates albedo, normals, and lighting of an indoor scene from a single image. Our key contribution is the Residual Appearance Renderer (RAR), which can be trained to synthesize complex appearance effects (e.g., inter-reflection, cast shadows, near-field illumination, and realistic shading), which would be neglected otherwise. This enables us to perform self-supervised learning on real data using a reconstruction loss, based on re-synthesizing the input image from the estimated components. We finetune with real data after pretraining with synthetic data. Experimental results show that our approach outperforms state-of-the-art methods that estimate one or more scene attributes.
Role of RAR in albedo estimation
For more qualitative and quantitative comparisons, please see our paper.
For downloading and visualizing more estimated results obtained by our algorithm: please visit the following link.
For any additional questions or clarifications, please feel free to contact me (Soumyadip) at soumya91 @ cs.washington.edu.
|
|
|
|
|
|
|
|
University of Maryland, College Park University of Washington |
 |
Neural Inverse Rendering of an Indoor Scene From a Single Image. We propose a self-supervised approach for inverse rendering. We jointly decompose an indoor scene image into albedo, surface normal and environment map lighting (top). Our method outperforms state-of-the-art approaches (bottom) that solve for only one of the scene attributes, i.e. albedo (Li et. al.), normal (Zhang et. al.) and lighting (Gardner et. al.). |
Inverse rendering aims to estimate physical attributes of a scene, e.g., reflectance, geometry, and lighting, from image(s). Inverse rendering has been studied primarily for single objects or with methods that solve for only one of the scene attributes. We propose the first learning based approach that jointly estimates albedo, normals, and lighting of an indoor scene from a single image. Our key contribution is the Residual Appearance Renderer (RAR), which can be trained to synthesize complex appearance effects (e.g., inter-reflection, cast shadows, near-field illumination, and realistic shading), which would be neglected otherwise. This enables us to perform self-supervised learning on real data using a reconstruction loss, based on re-synthesizing the input image from the estimated components. We finetune with real data after pretraining with synthetic data. Experimental results show that our approach outperforms state-of-the-art methods that estimate one or more scene attributes.
 |
Soumyadip Sengupta, Jinwei Gu, Kihwan Kim, Guilin Liu, David W. Jacobs, Jan Kautz. Neural Inverse Rendering of an Indoor Scene From a Single Image In ICCV 2019. |
| Overview of our approach. Our Inverse Rendering Network (IRN) predicts albedo, normals and illumination map. We train on unlabeled real images using self-supervised reconstruction loss. Reconstruction loss consists of a closed-form Direct Renderer with no learnable parameters and the proposed Residual Appearance Renderer (RAR), which learns to predict complex appearance effects. |
Results
|
|
|
|
 Comparison with Zhang et. al. |
 Comparison with Li et. al. |
|
|
|
|
 Comparison with Gardner et. al. |
 |
Acknowledgements |