Q
Qian He
Publications - 9
Citations - 50
Qian He is an academic researcher. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 3, co-authored 9 publications receiving 50 citations.
Papers
More filters
Journal ArticleDOI
CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP
TL;DR: Qualitative and quantitative evaluations verify that the self-supervised CLIP-GEN scheme significantly outperforms optimization-based text-to-image methods in terms of image quality while not compromising the text-image matching.
Proceedings ArticleDOI
Region-Aware Face Swapping
TL;DR: A novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner and proposes a Face Mask Predictor (FMP) module incorporated with StyleGAN2 to predict identity-relevant soft facial masks in an unsupervised manner that is more practical for generating harmonioushigh-resolution faces.
Proceedings ArticleDOI
XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation
TL;DR: A self-supervised cross-modality pre-training strategy and a cross- modality transformer-based encoder that is conditioned jointly on the glyph image and the corresponding stroke labels are proposed, which facilitates the content-style disentanglement and modeling style representations of all scales.
Journal ArticleDOI
Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field
TL;DR: Wang et al. as mentioned in this paper propose a compositional neural radiance field (CNeRF) for semantic 3D-aware portrait synthesis and manipulation, which divides the image by semantic regions and learns an independent neural radiances field for each region, and finally fuses them and renders the complete image.
Journal ArticleDOI
Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation
TL;DR: Zhang et al. as mentioned in this paper proposed a new approach for flexible image translation by learning a layout-aware image condition together with a text condition, which co-encodes images and text into a new domain during the training phase.