ClothFlow: A Flow-Based Model for Clothed Person Generation

Han, Xintong; Huang, Weilin; Hu, Xiaojun; Scott, Matthew R.

doi:10.1109/iccv.2019.01057

Cited by 222 publications

(187 citation statements)

References 29 publications

Supporting

Mentioning

187

Contrasting

Order By: Relevance

“…Qualitative comparison. Figure 4 shows Figure 6: Qualitative results on DeepFashion dataset compared with CF [HHHS19]. Please zoom in for details.…”

Section: Resultsmentioning

confidence: 99%

“…Han et al [HHHS19] used synthesized parsing map to estimate a cloth flow mapping, warped image features to generate the clothing image without body, and concatenated the source image to synthesize the final result. Dong et al…”

Section: Human Pose Transfermentioning

confidence: 99%

“…We also compare our method with two semantic-guided methods, SG [DLG * 18] and CF [HHHS19], in Figure 5 and Figure 6, respectively. Due to lack of their codes, we use the results presented in their papers.…”

Section: Comparisonmentioning

confidence: 99%

“…Moreover, the matrix uses warped image features and is implemented only once, which is difficult to generate reasonable results for unknown regions. Han et al [HHHS19] proposed a three-stage framework by adding a rendering network at the final stage to avoid the artifacts induced by wrong flows. However, these flow/transformation-based methods are difficult to deal with large transformation between source image and target image.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Human Pose Transfer by Adaptive Hierarchical Deformation

Zhang

Liu

2020

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Qualitative comparison. Figure 4 shows Figure 6: Qualitative results on DeepFashion dataset compared with CF [HHHS19]. Please zoom in for details.…”

Section: Resultsmentioning

confidence: 99%

Section: Human Pose Transfermentioning

confidence: 99%

Section: Comparisonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Human Pose Transfer by Adaptive Hierarchical Deformation

Zhang

Liu

2020

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…There also exists method [42] which used a attentive bidirectional GAN to better refine the quality of person image in two stage. In order to better align the in-shop cloth to the target pose, Han et al [12] presented an appearance-flow-based generation model named ClothFlow to learn the geometric changes and naturally transfer the cloth and appearance of people to synthesised novel images.…”

Section: Virtual Try-onmentioning

confidence: 99%

Down to the Last Detail

Wang

Sha

Zhang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Virtual try-on has attracted lots of research attention due to its potential applications in e-commerce, virtual reality and fashion design. However, existing methods can hardly preserve the finegrained details (e.g., clothing texture, facial identity, hair style, skin tone) during generation, due to the non-rigid body deformation and multi-scale details. In this work, we propose a multi-stage framework to synthesize person images, where fine-grained details can be well preserved. To address the long-range translation and rich-details generation, we propose a Tree-Block (tree dilated fusion block) to replace standard ResNet-block where applicable. Notably, multi-scale feature maps can be smoothly fused for finegrained detail generation, by incorporating larger spatial context at multiple scales. With a delicate end-to-end training scheme, our whole framework can be jointly optimized for results with significantly better visual fidelity and richer details. Moreover, we also explore the potential application in video-based virtual try-on. By harnessing the well-trained image generator and an extra videolevel adaptor, a model photo can be well animated with a driving pose sequence. Extensive evaluations on standard datasets and user study demonstrate that our proposed framework achieves the stateof-the-art results, especially in preserving visual details in clothing texture and facial identity. Our implementation is publicly available via this URL.

show abstract

Unselfie: Translating Selfies to Neutral-Pose Portraits in the Wild

Lin²,

Barnes³

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Due to the ubiquity of smartphones, it is popular to take photos of one's self, or "selfies." Such photos are convenient to take, because they do not require specialized equipment or a third-party photographer. However, in selfies, constraints such as human arm length often make the body pose look unnatural. To address this issue, we introduce unselfie, a novel photographic transformation that automatically translates a selfie into a neutral-pose portrait. To achieve this, we first collect an unpaired dataset, and introduce a way to synthesize paired training data for self-supervised learning. Then, to unselfie a photo, we propose a new three-stage pipeline, where we first find a target neutral pose, inpaint the body texture, and finally refine and composite the person on the background. To obtain a suitable target neutral pose, we propose a novel nearest pose search module that makes the reposing task easier and enables the generation of multiple neutral-pose results among which users can choose the best one they like. Qualitative and quantitative evaluations show the superiority of our pipeline over alternatives.

show abstract

ClothFlow: A Flow-Based Model for Clothed Person Generation

Cited by 222 publications

References 29 publications

Human Pose Transfer by Adaptive Hierarchical Deformation

Human Pose Transfer by Adaptive Hierarchical Deformation

Down to the Last Detail

Unselfie: Translating Selfies to Neutral-Pose Portraits in the Wild

Contact Info

Product

Resources

About