In‐the‐wild Material Appearance Editing using Perceptual Attributes

Subías, J. Daniel; Lagunas, Manuel

doi:10.1111/cgf.14765

Cited by 5 publications

(1 citation statement)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discussion While other algorithms for dimensionality reduction exist (e.g., multidimensional scaling or kernel principal component analysis) we chose the IsoMap algorithm since it works well with arbitrary distance matrices and handles well non‐linear spaces [TdL00]. Other alternatives using neural networks, following previous works on perceptual spaces for material appearance [LMS*19; DLC*22; SL23], were considered, but we found that IsoMap works well in our case, and produces stable and meaningful manifolds that can be easily navigated, while the latent spaces of neural‐based methods might lead to unintuitive spaces and would require re‐training with extensive labeled data for translucent appearance.…”

Section: A Perceptually Meaningful Space For Translucent Appearancementioning

confidence: 99%

Navigating the Manifold of Translucent Appearance

Lanza,

Masia,

Jarabo

2024

Computer Graphics Forum

View full text Add to dashboard Cite

We present a perceptually‐motivated manifold for translucent appearance, designed for intuitive editing of translucent materials by navigating through the manifold. Classic tools for editing translucent appearance, based on the use of sliders to tune a number of parameters, are challenging for non‐expert users: These parameters have a highly non‐linear effect on appearance, and exhibit complex interplay and similarity relations between them. Instead, we pose editing as a navigation task in a low‐dimensional space of appearances, which abstracts the user from the underlying optical parameters. To achieve this, we build a low‐dimensional continuous manifold of translucent appearance that correlates with how humans perceive this type of materials. We first analyze the correlation of different distance metrics in image space with human perception. We select the best‐performing metric to build a low‐dimensional manifold, which can be used to navigate the space of translucent appearance. To evaluate the validity of our proposed manifold within its intended application scenario, we build an editing interface that leverages the manifold, and relies on image navigation plus a fine‐tuning step to edit appearance. We compare our intuitive interface to a traditional, slider‐based one in a user study, demonstrating its effectiveness and superior performance when editing translucent objects.

show abstract