Automatic texture exemplar extraction based on global and local textureness measures

Wu, Huisi; Lyu, Xiaomeng; Wen, Zhenkun

doi:10.1007/s41095-018-0106-z

Cited by 10 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, we want a crop which when embedded will give a good synthesized texture. Thus, instead of taking the mean, we can select a representative crop for the surface using a textureness score [7,28]. We use the difference of VGG statistics (employed as a similarity metric by Henzler et al [10]) between the synthesized texture and the conditioned surface crop as a proxy for the textureness score.…”

Section: Texture Synthesis For Observed Surfacesmentioning

confidence: 99%

Plan2Scene: Converting Floorplans to 3D Scenes

Vidanapathirana¹,

Wu²,

Furukawa³

et al. 2021

Preprint

View full text Add to dashboard Cite

We address the task of converting a floorplan and a set of associated photos of a residence into a textured 3D mesh model, a task which we call Plan2Scene. Our system 1) lifts a floorplan image to a 3D mesh model; 2) synthesizes surface textures based on the input photos; and 3) infers textures for unobserved surfaces using a graph neural network architecture. To train and evaluate our system we create indoor surface texture datasets, and augment a dataset of floorplans and photos from prior work with rectified surface crops and additional annotations. Our approach handles the challenge of producing tileable textures for dominant surfaces such as floors, walls, and ceilings from a sparse set of unaligned photos that only partially cover the residence. Qualitative and quantitative evaluations show that our system produces realistic 3D interior models, outperforming baseline approaches on a suite of texture quality metrics and as measured by a holistic user study.

show abstract

Section: Texture Synthesis For Observed Surfacesmentioning

confidence: 99%

Plan2Scene: Converting Floorplans to 3D Scenes

Vidanapathirana¹,

Wu²,

Furukawa³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Instead of constant colors or textures, the tiles in image mosaics are themselves images. The tiles are not created by texture synthesis [17,18], but retrieved from a database. The appearances of these images resemble the local content of the target image, and together represent the content of the whole target image.…”

Section: Image Mosaicsmentioning

confidence: 99%

Discernible image mosaic with edge-aware adaptive tiles

Ding

Zhang

et al. 2019

Comp. Visual Media

View full text Add to dashboard Cite

We present a novel method to produce discernible image mosaics, with relatively large image tiles replaced by images drawn from a database, to resemble a target image. Compared to existing works on image mosaics, the novelty of our method is twofold. Firstly, believing that the presence of visual edges in the final image mosaic strongly supports image perception, we develop an edge-aware photo retrieval scheme which emphasizes the preservation of visual edges in the target image. Secondly, unlike most previous works which apply a predetermined partition to an input image, our image mosaics are composed of adaptive tiles, whose sizes are determined based on the available images in the database and the objective of maximizing resemblance to the target image. We show discernible image mosaics obtained by our method, using image collections of only moderate size. To evaluate our method, we conducted a user study to validate that the image mosaics generated present both globally and locally appropriate visual impressions to the human observers. Visual comparisons with existing techniques demonstrate the superiority of our method in terms of mosaic quality and perceptibility.

show abstract

An algorithm for generating uniform points on a cylindrical surface

Zhu

2020

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The existing Poisson-disk sampling methods work well in traditional space, whatever two dimensional or three dimensional space. However, there are few methods on generating random points in non-Euclid space. For generating uniform points on the cylinder surface, we propose an algorithm which combines Poisson-Disk sampling algorithm with cylindrical distance constraints in this paper. Experiment results show that the quality of the point set generated by the proposed algorithm is better than that generated by the pseudo-random number method in both uniformity and stability.

show abstract

Automatic texture exemplar extraction based on global and local textureness measures

Cited by 10 publications

References 23 publications

Plan2Scene: Converting Floorplans to 3D Scenes

Plan2Scene: Converting Floorplans to 3D Scenes

Discernible image mosaic with edge-aware adaptive tiles

An algorithm for generating uniform points on a cylindrical surface

Contact Info

Product

Resources

About