Transfer of albedo and local depth variation to photo-textures

Melendez, Francho; Glencross, Mashhuda; Starck, Jon; Ward, Greg

doi:10.1145/2414688.2414694

Cited by 4 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All these methods share the strength of providing high-level control on their output thanks to the exemplars, a feature that we now provide in the context of SVBRDF capture and design. Closer to our application domain is the work by Melendez et al [MGSJW12], who used patch-based texture synthesis to transfer diffuse albedo and depth variations from small material exemplars to large façade images. However, their approach assumes that every pixel of the target can be put in correspondence to similar pixels of the exemplar, which yields visual artifacts when the exemplars do not contain all the material variations of the target image (see Fig.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Guided Fine‐Tuning for Large‐Scale Material Transfer

Deschaintre

Drettakis²,

Bousseau³

2020

Computer Graphics Forum

View full text Add to dashboard Cite

SVBRDFs to a target picture. This approach allows the capture of large planar surfaces taken with ambient lighting (far left), by extracting the SVBRDF exemplars from close-up flash pictures (lower left), as well as the creation of plausible SVBRDFs from internet pictures by using existing artist-designed materials as exemplars (right). Please see supplemental materials for high-resolution SVBRDF parameter maps and animated renderings of all our results, which give a much better impression of the material properties.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Qualitative comparisons. Our approach is related to the method by Melendez et al [MGSJW12], which transfers diffuse albedo and displacement maps using patch-based texture synthesis akin to image analogies [HJO * 01]. We reproduced this approach with the state-of-the-art patch-based synthesis algorithm of Fišer et al…”

Section: Comparisonsmentioning

confidence: 99%

Guided Fine‐Tuning for Large‐Scale Material Transfer

Deschaintre

Drettakis²,

Bousseau³

2020

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…There are a few methods that follow a similar paradigm to ours, transferring pre-estimated SVBRDF maps to a larger material sample. Using PatchMatch texture synthesis, Melendez et al [4] transfer displacement and albedo maps from small samples of the materials. Their method is limited to daylight illumination and materials present in fac ¸ades.…”

Section: Svbrdf Estimationmentioning

confidence: 99%

“…This propagation requires adapting to the local and global spatial regularities of the material, which can be challenging if the input guidance image suffers from inhomogeneous illumination, unknown scale, or affine distortions (see Figure 1, second column). The problem has been formulated within the context of image analogies [3], and addressed via PatchMatch-based synthesis [4], look-up-tables [5], or neural networks [6], by Fig. 1: The input exemplars on the left-bottom are transferred to the input guidances (second column) using images of the material taken under multiple illuminations (photometric input) as training data.…”

Section: Introductionmentioning

confidence: 99%

Neural Photometry-guided Visual Attribute Transfer

Rodriguez-Pardo,

Garces

2021

Preprint

View full text Add to dashboard Cite

We present a deep learning-based method for propagating spatially-varying visual material attributes (e.g. texture maps or image stylizations) to larger samples of the same or similar materials. For training, we leverage images of the material taken under multiple illuminations and a dedicated data augmentation policy, making the transfer robust to novel illumination conditions and affine deformations. Our model relies on a supervised image-to-image translation framework and is agnostic to the transferred domain; we showcase a semantic segmentation, a normal map, and a stylization. Following an image analogies approach, the method only requires the training data to contain the same visual structures as the input guidance. Our approach works at interactive rates, making it suitable for material edit applications. We thoroughly evaluate our learning methodology in a controlled setup providing quantitative measures of performance. Last, we demonstrate that training the model on a single material is enough to generalize to materials of the same type without the need for massive datasets.

show abstract

“…Modern graphic engines enable advanced textures with dynamic features, such as transparencies or reflections (Figure 4). However, these effects typically need to be applied manually as they are difficult to detect automatically using the methods of photogrammetry (but see Melendez et al, 2012, for an approach of optimizing materials from photographs).…”

Section: Technical Foundationmentioning

confidence: 99%

A Review of Photogrammetry and Photorealistic 3D Models in Education From a Psychological Perspective

et al. 2020

View full text Add to dashboard Cite

Until sufficient practical experience and documented examples are available, emerging technological methods to create educational content typically require in-depth knowledge from different fields in order to apply them in the most beneficial way. The method of creating photorealistic 3D models (PR3DMs) of real-world objects with the methods of photogrammetry is an example of such emerging technologies. This paper discusses the fundamental concepts of photogrammetry to provide an overview of the necessary basic knowledge for educators and researchers interested in the presentation of realistic virtual materials. Additionally, a deeper introduction to basic psychological processes while learning with photorealistic materials is presented. This provides deeper insights into potentials and issues, as well as an overview of the most crucial research gaps in learning with PR3DMs. Finally, current and future applications, as well as the potential for learning topics apart from factual knowledge, such as emotional or behavioral outcomes, are discussed.

show abstract

Transfer of albedo and local depth variation to photo-textures

Cited by 4 publications

References 43 publications

Guided Fine‐Tuning for Large‐Scale Material Transfer

Guided Fine‐Tuning for Large‐Scale Material Transfer

Neural Photometry-guided Visual Attribute Transfer

A Review of Photogrammetry and Photorealistic 3D Models in Education From a Psychological Perspective

Contact Info

Product

Resources

About