Intrinsic Image Decomposition via Ordinal Shading

Abstract

Intrinsic decomposition is a fundamental mid-level vision problem that plays a crucial role in various inverse rendering and computational photography pipelines. Generating highly accurate intrinsic decompositions is an inherently under-constrained task that requires precisely estimating continuous-valued shading and albedo. In this work, we achieve high-resolution intrinsic decomposition by breaking the problem into two parts. First, we present a dense ordinal shading formulation using a shift- and scale-invariant loss in order to estimate ordinal shading cues without restricting the predictions to obey the intrinsic model. We then combine low- and high-resolution ordinal estimations using a second network to generate a shading estimate with both global coherency and local details. We encourage the model to learn an accurate decomposition by computing losses on the estimated shading as well as the albedo implied by the intrinsic model. We develop a straightforward method for generating dense pseudo ground truth using our model’s predictions and multi-illumination data, enabling generalization to in-the-wild imagery. We present exhaustive qualitative and quantitative analysis of our predicted intrinsic components against state-of-the-art methods. Finally, we demonstrate the real-world applicability of our estimations by performing otherwise difficult editing tasks such as recoloring and relighting.

Implementation

GitHub Repository

Video

Paper

Dataset

MID Intrinsics Brief Description We present the first dense, real-world, and large-scale dataset for intrinsic image decomposition. Our dataset was derived from the Multi-Illumination Dataset by Murmann et al. and consists of 1000 scenes under 25 different illuminations each, with 1000 unique albedo maps and 25.000 image - RGB shading pairs. This dataset accompanies our ACM Trans. Graph. 2023 paper. BibTeX @ARTICLE{careagaIntrinsic, author={Chris Careaga and Ya\u{g}{\i}z Aksoy}, title={Intrinsic Image Decomposition via Ordinal Shading}, journal={ACM Trans. Graph.}, year={2023}, }

BibTeX

License

The methodology presented in this work is safeguarded under intellectual property protection. For inquiries regarding licensing opportunities, kindly reach out to SFU Technology Licensing Office <tlo_dir ατ sfu δøτ ca> and Dr. Yağız Aksoy <yagiz ατ sfu δøτ ca>.

Related Publications

Intrinsic Harmonization for Illumination-Aware Compositing Chris Careaga, S. Mahdi H. Miangoleh, and Yağız Aksoy SIGGRAPH Asia, 2023 Abstract Despite significant advancements in network-based image harmonization techniques, there still exists a domain disparity between typical training pairs and real-world composites encountered during inference. Most existing methods are trained to reverse global edits made on segmented image regions, which fail to accurately capture the lighting inconsistencies between the foreground and background found in composited images. In this work, we introduce a self-supervised illumination harmonization approach formulated in the intrinsic image domain. First, we estimate a simple global lighting model from mid-level vision representations to generate a rough shading for the foreground region. A network then refines this inferred shading to generate a harmonious re-shading that aligns with the background scene. In order to match the color appearance of the foreground and background, we utilize ideas from prior harmonization approaches to perform parameterized image edits in the albedo domain. To validate the effectiveness of our approach, we present results from challenging real-world composites and conduct a user study to objectively measure the enhanced realism achieved compared to state-of-the-art harmonization methods. Manuscript & more BibTeX @INPROCEEDINGS{careagaCompositing, author={Chris Careaga and S. Mahdi H. Miangoleh and Ya\u{g}{\i}z Aksoy}, title={Intrinsic Harmonization for Illumination-Aware Compositing}, booktitle={Proc. SIGGRAPH Asia}, year={2023}, }

Computational Flash Photography through Intrinsics Sepideh Sarajian Maralan, Chris Careaga, and Yağız Aksoy CVPR, 2023 Abstract Flash is an essential tool as it often serves as the sole controllable light source in everyday photography. However, the use of flash is a binary decision at the time a photograph is captured with limited control over its characteristics such as strength or color. In this work, we study the computational control of the flash light in photographs taken with or without flash. We present a physically motivated intrinsic formulation for flash photograph formation and develop flash decomposition and generation methods for flash and no-flash photographs, respectively. We demonstrate that our intrinsic formulation outperforms alternatives in the literature and allows us to computationally control flash in in-the-wild images. Manuscript & more BibTeX @INPROCEEDINGS{Maralan2023Flash, author={Sepideh Sarajian Maralan and Chris Careaga and Ya\u{g}{\i}z Aksoy}, title={Computational Flash Photography through Intrinsics}, journal={Proc. CVPR}, year={2023}, }