Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image

Li, Zhengqin; Sunkavalli, Kalyan; Chandraker, Manmohan

doi:10.1007/978-3-030-01219-9_5

Cited by 137 publications

(129 citation statements)

References 44 publications

Supporting

Mentioning

129

Contrasting

Order By: Relevance

“…For example, it is shown that depth and normals may be estimated from a single image [6,7,50] or multiple images [38]. Parametric BRDF may be estimated either from an RGBD sequence of an object [25,15] or for planar surfaces [21]. Lighting may also be estimated from images, either as an environment map [8,10], or spherical harmonics [48] or point lights [46].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Neural Inverse Rendering of an Indoor Scene From a Single Image

Sengupta

Kim³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

136

View full text Add to dashboard Cite

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. To this end we use physically-based rendering to create a largescale synthetic dataset, which is a significant improvement over prior datasets. Experimental results show that our approach outperforms state-of-the-art methods that estimate one or more scene attributes.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Second, inverse rendering of a scene is particularly challenging, compared to single objects, due to complex appearance effects (e.g., inter-reflection, cast shadows, near-field illumination, and realistic shading). Some existing works [8,21,47,19] Li [19] PBRS [46] Gardner [8] Inverse Rendering Network (IRN) Input Image…”

Section: Introductionmentioning

confidence: 99%

Neural Inverse Rendering of an Indoor Scene From a Single Image

Sengupta

Kim³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

136

View full text Add to dashboard Cite

show abstract

“…A number of methods have been proposed that rely on deep learning to estimate the reflectance properties and meso‐structure from a single photograph under flash lighting [DAD∗18, LSC18, AAL16, LXR∗18] or under natural lighting [LDPT17, YLD∗18]. While promising, these methods either control the incident lighting, and/or are limited to planar samples only.…”

Section: Related Workmentioning

confidence: 99%

On‐Site Example‐Based Material Appearance Acquisition

Lin

Peers

Ghosh

2019

Computer Graphics Forum

View full text Add to dashboard Cite

We present a novel example‐based material appearance modeling method suitable for rapid digital content creation. Our method only requires a single HDR photograph of a homogeneous isotropic dielectric exemplar object under known natural illumination. While conventional methods for appearance modeling require prior knowledge on the object shape, our method does not, nor does it recover the shape explicitly, greatly simplifying on‐site appearance acquisition to a lightweight photography process suited for non‐expert users. As our central contribution, we propose a shape‐agnostic BRDF estimation procedure based on binary RGB profile matching. We also model the appearance of materials exhibiting a regular or stationary texture‐like appearance, by synthesizing appropriate mesostructure from the same input HDR photograph and a mesostructure exemplar with (roughly) similar features. We believe our lightweight method for on‐site shape‐agnostic appearance acquisition presents a suitable alternative for a variety of applications that require plausible “rapid‐appearance‐modeling”.

show abstract

“…Several research projects address materials and their appearance in images. Georgoulis et al [14] use synthetic images of specular objects as training data to estimate reflectance and illumination, Li et al [19] recover the SVBRDF of a material also using rendered training data, and Yang et al [30] use synthetic images containing metal and rubber materials as training data for visual recognition. These authors however do not consider segmentation.…”

Section: Related Workmentioning

confidence: 99%

Material-Based Segmentation of Objects

et al. 2019

View full text Add to dashboard Cite

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

show abstract

Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image

Cited by 137 publications

References 44 publications

Neural Inverse Rendering of an Indoor Scene From a Single Image

Neural Inverse Rendering of an Indoor Scene From a Single Image

On‐Site Example‐Based Material Appearance Acquisition

Material-Based Segmentation of Objects

Contact Info

Product

Resources

About