paper-with-me

홈 › Papers

Neural Texture Extraction and Distribution for Controllable Person Image Synthesis

2022-04-13 · CVPR 2022 1 · Yurui Ren, Xiaoqing Fan, Ge Li, Shan Liu, Thomas H. Li

We deal with the controllable person image synthesis task which aims to re-render a human from a reference image with explicit control over body pose and appearance. Observing that person images are highly structured, we propose to generate desired images by extracting and distributing semantic entities of reference images. To achieve this goal, a neural texture extraction and distribution operation based on double attention is described. This operation first extracts semantic neural textures from reference feature maps. Then, it distributes the extracted neural textures according to the spatial distributions learned from target poses. Our model is trained to predict human images in arbitrary poses, which encourages it to extract disentangled and expressive neural textures representing the appearance of different semantic entities. The disentangled representation further enables explicit appearance control. Neural textures of different reference images can be fused to control the appearance of the interested areas. Experimental comparisons show the superiority of the proposed model. Code is available at https://github.com/RenYurui/Neural-Texture-Extraction-Distribution.

📄 PDF Abstract BibTeX arXiv:2204.06160

Code (1)

renyurui/neural-texture-extraction-distribution 공식 구현 pytorch

Tasks

Image Generation

Similar Papers 제목 키워드 기반

UVMap-ID: A Controllable and Personalized UV Map Generative Model

2024-04-22 · Weijie Wang, Jichao Zhang, Chang Liu, Xia Li 외

Recently, diffusion models have made significant strides in synthesizing realistic 2D human images based on provided text prompts. Building upon this, researchers have extended 2D text-to-image diffusion models into the …

Attribute

Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization

2021-05-31 · Jichao Zhang, Aliaksandr Siarohin, Hao Tang, Enver Sangineto 외

Controllable person image generation aims to produce realistic human images with desirable attributes such as a given pose, cloth textures, or hairstyles. However, the large spatial misalignment between source and target…

Image GenerationImage-to-Image TranslationPose TransferTranslation

Correspondence Learning for Controllable Person Image Generation

2020-12-23 · Shilong Shen

We present a generative model for controllable person image synthesis,as shown in Figure , which can be applied to pose-guided person image synthesis, $i.e.$, converting the pose of a source person image to the target po…

AttributeImage Generation

Cross Attention Based Style Distribution for Controllable Person Image Synthesis

2022-08-01 · Xinyue Zhou, Mingyu Yin, Xinyuan Chen, Li Sun 외

Controllable person image synthesis task enables a wide range of applications through explicit control over body pose and appearance. In this paper, we propose a cross attention based style distribution module that compu…

Image GenerationPose TransferVirtual Try-on

Disentangled Representation Learning for Controllable Person Image Generation

2023-12-10 · Wenju Xu, Chengjiang Long, Yongwei Nie, Guanghui Wang

In this paper, we propose a novel framework named DRL-CPG to learn disentangled latent representation for controllable person image generation, which can produce realistic person images with desired poses and human attri…

AttributeDecoderImage GenerationRepresentation Learning