![]() ![]() In this paper, we explore the task of generating photo-realistic face images from lines. Extensive experimental results on two challenging benchmarks, have demonstrated the effectiveness of the proposed approach. A hierarchical network, consisting of multi-stacked bidirectional LSTMs and an attention block, is developed to extract effective textual features from text descriptions of pedestrians. Moreover, an attribute graph convolutional network is proposed to learn visual attributes of pedestrians, which possess better descriptiveness, interpretability and robustness compared to pedestrian appearance. The latter is to distinguish the features from different modalities and boost the learning of modality-invariant features. The former is to improve intra-modality discrimination and inter-modality invariance towards confusing the modality discriminator. It is more applicable compared to person search with image/video query, \textit, cross-modal learner and modality discriminator, playing a min-max game in adversarial learning way. The newly emerging task of person search with natural language query aims at retrieving the target pedestrian by a text description of the pedestrian. We conduct extensive experiments and the results demonstrate the superiority of our model over existing methods on both image quality and model generalization to hand-drawn sketches. A novel spatial attention pooling (SAP) is designed to adaptively handle stroke distortions which are spatially varying to support various stroke styles and different levels of details. To address this problem, we propose DeepFacePencil, an effective tool that is able to generate photo-realistic face images from hand-drawn sketches, based on a novel dual generator image translation network during training. However, these synthesized edge maps strictly align with the edges of the corresponding face images, which limit their generalization ability to real hand-drawn sketches with vast stroke diversity. ![]() They typically utilize synthesized edge maps of face images as training data. Existing image-to-image translation methods require a large-scale dataset of paired sketches and images for supervision. In this paper, we explore the task of generating photo-realistic face images from hand-drawn sketches. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |