76 citations · 494 across the 38 of their papers we have counts for
40 papers
Neural Point-based Volumetric Avatar: Surface-guided Neural Points for Efficient and Photorealistic Volumetric Head Avatar
Cong Wang, Di Kang, Yan-Pei Cao +3
Rendering photorealistic and dynamically moving human heads is crucial for ensuring a pleasant and immersive experience in AR/VR and video conferencing applications. However, exist…
Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
Jiaxu Zhang, Junwu Weng, Di Kang +7
A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a…
Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors
Zhangyang Xiong, Di Kang, Derong Jin +4
Fast generation of high-quality 3D digital humans is important to a vast number of applications ranging from entertainment to professional concerns. Recent advances in differentiab…
Audio2Gestures: Generating Diverse Gestures from Audio
Jing Li, Di Kang, Wenjie Pei +4
People may perform diverse gestures affected by various mental and physical factors when speaking the same sentences. This inherent one-to-many relationship makes co-speech gesture…
Learning Audio-Driven Viseme Dynamics for 3D Face Animation
Linchao Bao, Haoxian Zhang, Yue Qian +4
We present a novel audio-driven facial animation approach that can generate realistic lip-synchronized 3D facial animations from the input audio. Our approach learns viseme dynamic…
CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder
Ye Huang, Di Kang, Liang Chen +5
Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-…
FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction
Haoran Bai, Di Kang, Haoxian Zhang +2
We present a large-scale facial UV-texture dataset that contains over 50,000 high-quality texture UV-maps with even illuminations, neutral expressions, and cleaned facial regions,…
Smooth image-to-image translations with latent space interpolations
Yahui Liu, Enver Sangineto, Yajing Chen +5
Multi-domain image-to-image (I2I) translations can transform a source image according to the style of a target domain. One important, desired characteristic of these transformation…
NEURAL MARIONETTE: A Transformer-based Multi-action Human Motion Synthesis System
Weiqiang Wang, Xuefei Zhe, Qiuhong Ke +4
We present a neural network-based system for long-term, multi-action human motion synthesis. The system, dubbed as NEURAL MARIONETTE, can produce high-quality and meaningful motion…
Learning to Construct 3D Building Wireframes from 3D Line Clouds
Yicheng Luo, Jing Ren, Xuefei Zhe +4
Line clouds, though under-investigated in the previous work, potentially encode more compact structural information of buildings than point clouds extracted from multi-view images.…
PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-view Images
Zhangyang Xiong, Dong Du, Yushuang Wu +4
It is very challenging to accurately reconstruct sophisticated human geometry caused by various poses and garments from a single image. Recently, works based on pixel-aligned impli…
Semi-signed prioritized neural fitting for surface reconstruction from unoriented point clouds
Runsong Zhu, Di Kang, Ka-Hei Hui +6
Reconstructing 3D geometry from \emph{unoriented} point clouds can benefit many downstream tasks. Recent shape modeling methods mostly adopt implicit neural representation to fit a…
REALY: Rethinking the Evaluation of 3D Face Reconstruction
Zenghao Chai, Haoxian Zhang, Jing Ren +5
The evaluation of 3D face reconstruction results typically relies on a rigid shape alignment between the estimated 3D model and the ground-truth scan. We observe that aligning two…
CAR: Class-aware Regularizations for Semantic Segmentation
Ye Huang, Di Kang, Liang Chen +4
Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of ex…
PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis
Xianggang Yu, Jiapeng Tang, Yipeng Qin +4
We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images, for novel view synthesis. Previous solutions, such as pixelNeRF, rely…
Consistent 3D Hand Reconstruction in Video via self-supervised Learning
Zhigang Tu, Zhisheng Huang, Yujin Chen +4
We present a method for reconstructing accurate and consistent 3D hands from a monocular video. We observe that detected 2D hand keypoints and the image texture provide important c…
NeRFReN: Neural Radiance Fields with Reflections
Yuan-Chen Guo, Di Kang, Linchao Bao +2
Neural Radiance Fields (NeRF) has achieved unprecedented view synthesis quality using coordinate-based neural scene representations. However, NeRF's view dependency can only handle…
ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation
Yahui Liu, Yajing Chen, Linchao Bao +3
Recently, there has been an increasing interest in image editing methods that employ pre-trained unconditional image generators (e.g., StyleGAN). However, applying these methods to…
Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
Jing Li, Di Kang, Wenjie Pei +4
Generating conversational gestures from speech audio is challenging due to the inherent one-to-many mapping between audio and body motions. Conventional CNNs/RNNs assume one-to-one…
UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing
Meng Cao, Haozhi Huang, Hao Wang +6
Recent research has witnessed advances in facial image editing tasks including face swapping and face reenactment. However, these methods are confined to dealing with one specific…
Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
Yahui Liu, Enver Sangineto, Yajing Chen +6
Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequent…
Animatable Neural Radiance Fields from Monocular RGB Videos
Jianchuan Chen, Ying Zhang, Di Kang +4
We present animatable neural radiance fields (animatable NeRF) for detailed human avatar creation from monocular videos. Our approach extends neural radiance fields (NeRF) to the d…
Model-based 3D Hand Reconstruction via Self-Supervised Learning
Yujin Chen, Zhigang Tu, Di Kang +5
Reconstructing a 3D hand from a single-view RGB image is challenging due to various hand configurations and depth ambiguity. To reliably reconstruct a 3D hand from a monocular imag…
High-Fidelity 3D Digital Human Head Creation from RGB-D Selfies
Linchao Bao, Xiangkai Lin, Yajing Chen +9
We present a fully automatic system that can produce high-fidelity, photo-realistic 3D digital human heads with a consumer RGB-D selfie camera. The system only needs the user to ta…