Learning to generate line drawings that convey geometry and semantics

Chan, Caroline; Durand, Frédo; Isola, Phillip

doi:10.1109/cvpr52688.2022.00776

Cited by 52 publications

(33 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For sketch generation model S, we employ the latest image-to-sketching method [4] to convert input image x i into its corresponding sketch S(x i ).…”

Section: Sketch Generationmentioning

confidence: 99%

“…The sketching method [4] is an unsupervised model trained on unpaired data between photographs (domain A) and sketches (domain B). It setups an adversarial training network with generators G A , G B and discriminators D A , D B respectively for domain A and B.…”

Section: Sketch Generationmentioning

confidence: 99%

“…Taking advantage of the advances in the latest image-to-sketch research [4,7,8,13,24,26], we exploit the sketch to relieve unfairness while keeping the class or semantic information. Since sketches convey most semantic information from the original images, neural networks could also use them to make predictions without sacrificing much accuracy, especially where class discrimination relies little on the color information (i.e.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving Fairness in Image Classification via Sketching

Yao¹,

Cui²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Fairness is a fundamental requirement for trustworthy and human-centered Artificial Intelligence (AI) system. However, deep neural networks (DNNs) tend to make unfair predictions when the training data are collected from different sub-populations with different attributes (i.e. color, sex, age), leading to biased DNN predictions. We notice that such a troubling phenomenon is often caused by data itself, which means that bias information is encoded to the DNN along with the useful information (i.e. class information, semantic information). Therefore, we propose to use sketching to handle this phenomenon. Without losing the utility of data, we explore the image-to-sketching methods that can maintain useful semantic information for the target classification while filtering out the useless bias information. In addition, we design a fair loss to further improve the model fairness. We evaluate our method through extensive experiments on both general scene dataset and medical scene dataset. Our results show that the desired image-tosketching method improves model fairness and achieves satisfactory results among state-of-the-art (SOTA).

show abstract

“…For sketch generation model S, we employ the latest image-to-sketching method [4] to convert input image x i into its corresponding sketch S(x i ).…”

Section: Sketch Generationmentioning

confidence: 99%

Section: Sketch Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Fairness in Image Classification via Sketching

Yao¹,

Cui²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In total, we have 133 × 50 image queries. To obtain sketch queries, we use the method of Chan et al [17] to convert images into sketches.…”

Section: Model Retrievalmentioning

confidence: 99%

“…Similar to Table 2, We use the generated images as query for image-based model retrieval. For sketch-based evaluation we use the method of Chan et al [17] to convert generated images to sketch.…”

Section: Originalmentioning

confidence: 99%

Content-Based Search for Deep Generative Models

Lu¹,

Wang²,

Kumari³

et al. 2022

Preprint

View full text Add to dashboard Cite

Body Part Segmentation of Anime Characters

Ou,

Liu,

et al. 2024

Computer Animation & Virtual

View full text Add to dashboard Cite

Semantic segmentation is an important approach to present the perceptual semantic understanding of an image, which is of significant usage in various applications. Especially, body part segmentation is designed for segmenting body parts of human characters to assist different editing tasks, such as style editing, pose transfer, and animation production. Since segmentation requires pixel‐level precision in semantic labeling, classic heuristics‐based methods generally have unstable performance. With the deployment of deep learning, a great step has been taken in segmenting body parts of human characters in natural photographs. However, the existing models are purely trained on natural photographs and generally obtain incorrect segmentation results when applied on anime character images, due to the large visual gap between training data and testing data. In this article, we present a novel approach to achieving body part segmentation of cartoon characters via a pose‐based graph‐cut formulation. We demonstrate the use of the acquired body part segmentation map in various image editing tasks, including conditional generation, style manipulation, pose transfer, and video‐to‐anime.

show abstract

Learning to generate line drawings that convey geometry and semantics

Cited by 52 publications

References 51 publications

Improving Fairness in Image Classification via Sketching

Improving Fairness in Image Classification via Sketching

Content-Based Search for Deep Generative Models

Body Part Segmentation of Anime Characters

Contact Info

Product

Resources

About