Výsledky vyhledávání

Report

Learning Feature-Preserving Portrait Editing from Generated Pairs

Autor: Chen, Bowei, Zhi, Tiancheng, Zhu, Peihao, Sang, Shen, Liu, Jing, Luo, Linjie

Portrait editing is challenging for existing techniques due to difficulties in preserving subject features like identity. In this paper, we propose a training-based method leveraging auto-generated paired data to learn desired editing while ensuring

Externí odkaz: http://arxiv.org/abs/2407.20455

Zobrazit plný text záznamu

Report

FG-Net: Facial Action Unit Detection with Generalizable Pyramidal Features

Autor: Yin, Yufeng, Chang, Di, Song, Guoxian, Sang, Shen, Zhi, Tiancheng, Liu, Jing, Luo, Linjie, Soleymani, Mohammad

Automatic detection of facial Action Units (AUs) allows for objective facial expression analysis. Due to the high cost of AU labeling and the limited size of existing benchmarks, previous AU detection methods tend to overfit the dataset, resulting in

Externí odkaz: http://arxiv.org/abs/2308.12380

Zobrazit plný text záznamu

Report

ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs

Autor: Mu, Jiteng, Sang, Shen, Vasconcelos, Nuno, Wang, Xiaolong

While NeRF-based human representations have shown impressive novel view synthesis results, most methods still rely on a large number of images / views for training. In this work, we propose a novel animatable NeRF called ActorsNeRF. It is first pre-t

Externí odkaz: http://arxiv.org/abs/2304.14401

Zobrazit plný text záznamu

Report

AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning

Autor: Song, Guoxian, Xu, Hongyi, Liu, Jing, Zhi, Tiancheng, Shi, Yichun, Zhang, Jianfeng, Jiang, Zihang, Feng, Jiashi, Sang, Shen, Luo, Linjie

While substantial progresses have been made in automated 2D portrait stylization, admirable 3D portrait stylization from a single user photo remains to be an unresolved challenge. One primary obstacle here is the lack of high quality stylized 3D trai

Externí odkaz: http://arxiv.org/abs/2303.14297

Zobrazit plný text záznamu

Report

Tag-based annotation creates better avatars

Autor: Liu, Minghao, Cheng, Zeyu, Sang, Shen, Liu, Jing, Davis, James

Avatar creation from human images allows users to customize their digital figures in different styles. Existing rendering systems like Bitmoji, MetaHuman, and Google Cartoonset provide expressive rendering systems that serve as excellent design tools

Externí odkaz: http://arxiv.org/abs/2302.07354

Zobrazit plný text záznamu

Report

AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging

Autor: Sang, Shen, Zhi, Tiancheng, Song, Guoxian, Liu, Minghao, Lai, Chunpong, Liu, Jing, Wen, Xiang, Davis, James, Luo, Linjie

Stylized 3D avatars have become increasingly prominent in our modern life. Creating these avatars manually usually involves laborious selection and adjustment of continuous and discrete parameters and is time-consuming for average users. Self-supervi

Externí odkaz: http://arxiv.org/abs/2211.07818

Zobrazit plný text záznamu

Report

OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets

Autor: Li, Zhengqin, Yu, Ting-Wei, Sang, Shen, Wang, Sarah, Song, Meng, Liu, Yuhan, Yeh, Yu-Ying, Zhu, Rui, Gundavarapu, Nitesh, Shi, Jia, Bi, Sai, Xu, Zexiang, Yu, Hong-Xing, Sunkavalli, Kalyan, Hašan, Miloš, Ramamoorthi, Ravi, Chandraker, Manmohan

We propose a novel framework for creating large-scale photorealistic datasets of indoor scenes, with ground truth geometry, material, lighting and semantics. Our goal is to make the dataset creation process widely accessible, transforming scans into

Externí odkaz: http://arxiv.org/abs/2007.12868

Zobrazit plný text záznamu