paper-with-me

Papers

A Variational U-Net for Conditional Appearance and Shape Generation

2018-04-12 · CVPR 2018 6 · Patrick Esser, Ekaterina Sutter, Björn Ommer

Deep generative models have demonstrated great performance in image synthesis. However, results deteriorate in case of spatial deformations, since they generate images of objects directly, rather than modeling the intricate interplay of their inherent shape and appearance. We present a conditional U-Net for shape-guided image generation, conditioned on the output of a variational autoencoder for appearance. The approach is trained end-to-end on images, without requiring samples of the same object with varying pose or appearance. Experiments show that the model enables conditional image generation and transfer. Therefore, either shape or appearance can be retained from a query image, while freely altering the other. Moreover, appearance can be sampled due to its stochastic latent representation, while preserving shape. In quantitative and qualitative experiments on COCO, DeepFashion, shoes, Market-1501 and handbags, the approach demonstrates significant improvements over the state-of-the-art.

📄 PDF Abstract BibTeX arXiv:1804.04694

Code (2)

CompVis/vunet 공식 구현 tf
jhaux/VUNet pytorch

Tasks

Conditional Image GenerationImage Generation

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Shape-conditioned Image Generation by Learning Latent Appearance Representation from Unpaired Data

2018-11-29 · Yutaro Miyauchi, Yusuke Sugano, Yasuyuki Matsushita

Conditional image generation is effective for diverse tasks including training data synthesis for learning-based computer vision. However, despite the recent advances in generative adversarial networks (GANs), it is stil…

Conditional Image GenerationImage GenerationObject

3D Shape Generation and Completion through Point-Voxel Diffusion

2021-04-08 · ICCV 2021 10 · Linqi Zhou, Yilun Du, Jiajun Wu

We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike most existing models that learn to deterministically translate a latent vector to a shape, our model, Point-Voxel Diffusion (PVD), is…

3D Shape GenerationDenoising

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

2023-06-29 · NeurIPS 2023 11 · Zibo Zhao, Wen Liu, Xin Chen, Xianfang Zeng 외

We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional generative model from images or texts to…

3D Shape GenerationDecoder

AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation

2020-07-13 · ECCV 2020 8 · Xiaofeng Liu, Tong Che, Yiqun Lu, Chao Yang 외

This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision. In the viewer-centered coordinates, we construct an end-to-end trainable conditional variational …

3D ReconstructionDecoderNovel View Synthesis

CLOTH3D: Clothed 3D Humans

2019-12-05 · ECCV 2020 8 · Hugo Bertiche, Meysam Madadi, Sergio Escalera

This work presents CLOTH3D, the first big scale synthetic dataset of 3D clothed human sequences. CLOTH3D contains a large variability on garment type, topology, shape, size, tightness and fabric. Clothes are simulated on…