A Survey on Intrinsic Images: Delving Deep into Lambert and Beyond

Garcés, Elena; Rodríguez-Pardo, Carlos; Casas, Dan; López‐Moreno, Jorge

doi:10.1007/s11263-021-01563-8

Cited by 30 publications

(16 citation statements)

References 122 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reflectance properties can be obtained by a photometric stereo baseline or another alternative could be to use an intrinsic image decomposition approach from where the shading and albedo info can be retrieved and used accordingly such as from Garces. 44 The type of light sources can be considered as known and, thus, their properties are provided by the manufacturer. In order to achieve a more accurate ground truth, the luminous flux and temperature of each luminaire can be measured in lab conditions.…”

Section: Rgbd2lux Scenesmentioning

confidence: 99%

DeepLux: A data-driven method and benchmark for 3D illuminance maps estimation

Tsesmelis

Carissimi

Bue

2023

Lighting Research & Technology

View full text Add to dashboard Cite

In this paper, we propose a pipeline and benchmark, called DeepLux, for predicting illuminance on 3D point clouds. Classic algorithms for computing photometrically accurate illumination are based on numerical and analytical models which are generally computationally expensive, especially in scenarios with complex geometries. Unlike existing approaches, our algorithm is the first learning-based method that is able to predict accurate illuminance map information that could be used for real-time smart lighting applications. We also evaluate our approach on two complementary tasks, that is, light position and intensity estimation, which are important aspects in the field of lighting design. Additionally, we provide an extensive novel photometrically correct dataset, which we use for training and evaluating our approach. Experiments show that the proposed algorithm produces results on par with or even better than the state of the art (+8% average error in real tests) while achieving faster simulation timings than its analytical counterpart, especially in complex synthetic and real-world scenarios.

show abstract

Section: Rgbd2lux Scenesmentioning

confidence: 99%

DeepLux: A data-driven method and benchmark for 3D illuminance maps estimation

Tsesmelis

Carissimi

Bue

2023

Lighting Research & Technology

View full text Add to dashboard Cite

show abstract

“…Intrinsic image decomposition (IID) is traditionally described as the problem of decomposing an image into two layers: albedo, invariant color of the material, and shading, produced by the interaction between light and geometry [17]. The main relationship between IID and SfS is the estimation of intrinsic properties by analyzing a single image.…”

Section: B Intrinsic Image Decompositionmentioning

confidence: 99%

Applying Albedo Estimation and Implicit Neural Representations to Well-Posed Shape From Shading

et al. 2023

View full text Add to dashboard Cite

We present a method that improves the accuracy of depth maps by combining albedo estimation and implicit neural representations to the well-posed shape from shading. Because the estimation of depth information from a single image is an under-constrained problem, we apply certain physical constrains to convert the ill-posed shape from shading problem to a well-posed problem. Subsequently, we construct an image irradiance equation wherein the surface parameter representing albedo is estimated using a learning-based encoder-decoder network. By solving the equation using implicit neural representations, we can obtain a depth map of the original image. The proposed method achieves an accuracy of depth estimation from a single image with the mean absolute error (MAE) of 0.1510 and root mean square error (RMSE) of 0.1768, indicating superior performance to that of existing methods. Both simulation and real experiments have been carried out to verify the effectiveness of the proposed method.

show abstract

“…Works involved are implemented under different types of light sources (e.g., directional light [29], point light [42], or arbitrary lights [68,49,75]), targeting on multifarious types of objects (e.g., single arbitrary object [24], faces [77], or human body [32]) described in multiple material models (i.e, Blinn-Phong [38,71], general svBRDF [18,19], etc.). We solved a sub-topic in intrinsics decomposition targeting on the single arbitrary object with the highest complexity in image formation models [20], where the surface normal, the object's material, and the light are unknown. We also assume the light source to be directional and distant.…”

Section: Related Workmentioning

confidence: 99%

NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereo

Li¹,

Zheng²,

Feishi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Uncalibrated photometric stereo (UPS) is challenging due to the inherent ambiguity brought by unknown light. Existing solutions alleviate the ambiguity by either explicitly associating reflectance to light conditions or resolving light conditions in a supervised manner. This paper establishes an implicit relation between light clues and light estimation and solves UPS in an unsupervised manner. The key idea is to represent the reflectance as four neural intrinsics fields, i.e, position, light, specular, and shadow, based on which the neural light field is implicitly associated with light clues of specular reflectance and cast shadow. The unsupervised, joint optimization of neural intrinsics fields can be free from training data bias as well as accumulating error, and fully exploits all observed pixel values for UPS. Our method achieves a superior performance advantage over state-of-the-art UPS methods on public and self-collected datasets, under regular and challenging setups. The code will be released soon.

show abstract

A Survey on Intrinsic Images: Delving Deep into Lambert and Beyond

Cited by 30 publications

References 122 publications

DeepLux: A data-driven method and benchmark for 3D illuminance maps estimation

DeepLux: A data-driven method and benchmark for 3D illuminance maps estimation

Applying Albedo Estimation and Implicit Neural Representations to Well-Posed Shape From Shading

NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereo

Contact Info

Product

Resources

About