CoGS: Controllable Generation and Search from Sketch and Style

Ham, Cusuh; Tarres, Gemma Canet; Bui, Tien D.; Hays, James; Lin, Zhe; Collomosse, John

doi:10.1007/978-3-031-19787-1_36

Cited by 12 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…iSketch&Fill [30] Categorical Synthetic • Edgemap creation with Im2Pencil [54] and sketch-simplification [77] + ResNet [35] generator. CoGS [33] Categorical Synth+Real • Saliency with [40] for synthetic sketches + VQ-GAN [25] with VAE over codebook vectors.…”

Section: Paper Category Type Of Sketch Data Preparation + Salient Des...mentioning

confidence: 99%

“…This problem falls into the general image-to-image translation literature [41,64]. Indeed, some might recall prior arts (e.g., pix2pix [41], CycleGAN [105], MUNIT [38], Bi-cycleGAN [106]), and sketch-specific variants [33,86] primarily based on pix2pix [41] claiming to have tackled the exact problem. We are strongly inspired by these works, but significantly differ on one key aspect -we aim to generate from abstract human sketches, not accurate photo edgemaps which are already "photorealistic".…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Picture that Sketch: Photorealistic Image Generation from Abstract Sketches

Koley¹,

Bhunia²,

Sain³

et al. 2023

Preprint

View full text Add to dashboard Cite

Edgemap Sketch Sketch Sketch Sketch Sketch Existing Methods Proposed Method Figure 1. (a) Set of photos generated by the proposed method. (b) While existing methods can generate faithful photos from perfectly pixel-aligned edgemaps, they fall short drastically in case of highly deformed and sparse free-hand sketches. In contrast, our autoregressive sketch-to-photo generation model produces highly photorealistic outputs from highly abstract sketches.

show abstract

Section: Paper Category Type Of Sketch Data Preparation + Salient Des...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Picture that Sketch: Photorealistic Image Generation from Abstract Sketches

Koley¹,

Bhunia²,

Sain³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Compared with garment sketches, they are not flexible enough for the subsequent garment editing. Several methods [HLBK18, CMG21, HTB*22, CCC*23] work with a similar task of controllable image synthesis according to a sketch image and a reference or style image. While they are not designed for garment images, they suffer from the insufficient capability of texture generation and propagation.…”

Section: Related Workmentioning

confidence: 99%

Controllable Garment Image Synthesis Integrated with Frequency Domain Features

Liang,

Mo,

Gao

2023

Computer Graphics Forum

View full text Add to dashboard Cite

Using sketches and textures to synthesize garment images is able to conveniently display the realistic visual effect in the design phase, which greatly increases the efficiency of fashion design. Existing garment image synthesis methods from a sketch and a texture tend to fail in working on complex textures, especially those with periodic patterns. We propose a controllable garment image synthesis framework that takes as inputs an outline sketch and a texture patch and generates garment images with complicated and diverse texture patterns. To improve the performance of global texture expansion, we exploit the frequency domain features in the generative process, which are from a Fast Fourier Transform (FFT) and able to represent the periodic information of the patterns. We also introduce a perceptual loss in the frequency domain to measure the similarity of two texture pattern patches in terms of their intrinsic periodicity and regularity. Comparisons with existing approaches and sufficient ablation studies demonstrate the effectiveness of our method that is capable of synthesizing impressive garment images with diverse texture patterns while guaranteeing proper texture expansion and pattern consistency.

show abstract