no code implementations • 2 Apr 2024 • Tao Hu, Fangzhou Hong, Zhaoxi Chen, Ziwei Liu
FashionEngine automates the 3D human production with three key components: 1) A pre-trained 3D human diffusion model that learns to model 3D humans in a semantic UV latent space from 2D image training data, which provides strong priors for diverse generation and editing tasks.
1 code implementation • 4 Mar 2024 • Fangzhou Hong, Jiaxiang Tang, Ziang Cao, Min Shi, Tong Wu, Zhaoxi Chen, Shuai Yang, Tengfei Wang, Liang Pan, Dahua Lin, Ziwei Liu
Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping.
1 code implementation • 7 Feb 2024 • Jiaxiang Tang, Zhaoxi Chen, Xiaokang Chen, Tengfei Wang, Gang Zeng, Ziwei Liu
2) 3D Backbone: We present an asymmetric U-Net as a high-throughput backbone operating on multi-view images, which can be produced from text or single-view image input by leveraging multi-view diffusion models.
no code implementations • 10 Jan 2024 • Zhaoxi Chen, Gyeongsik Moon, Kaiwen Guo, Chen Cao, Stanislav Pidhorskyi, Tomas Simon, Rohan Joshi, Yuan Dong, Yichen Xu, Bernardo Pires, He Wen, Lucas Evans, Bo Peng, Julia Buffalini, Autumn Trimble, Kevyn McPhail, Melissa Schoeller, Shoou-I Yu, Javier Romero, Michael Zollhöfer, Yaser Sheikh, Ziwei Liu, Shunsuke Saito
To simplify the personalization process while retaining photorealism, we build a powerful universal relightable prior based on neural relighting from multi-view images of hands captured in a light stage with hundreds of identities.
1 code implementation • NeurIPS 2023 • Zhaoxi Chen, Fangzhou Hong, Haiyi Mei, Guangcong Wang, Lei Yang, Ziwei Liu
We present PrimDiffusion, the first diffusion-based framework for 3D human generation.
1 code implementation • 25 Oct 2023 • Guangcong Wang, Peng Wang, Zhaoxi Chen, Wenping Wang, Chen Change Loy, Ziwei Liu
In this paper, we present PERF, a 360-degree novel view synthesis framework that trains a panoramic neural radiance field from a single panorama.
1 code implementation • 5 Sep 2023 • Haonan Qiu, Zhaoxi Chen, Yuming Jiang, Hang Zhou, Xiangyu Fan, Lei Yang, Wayne Wu, Ziwei Liu
Our key insight is to decompose the portrait's reflectance from implicitly learned audio-driven facial normals and images.
1 code implementation • 1 Sep 2023 • Haozhe Xie, Zhaoxi Chen, Fangzhou Hong, Ziwei Liu
3D city generation is a desirable yet challenging task, since humans are more sensitive to structural distortions in urban environments.
Ranked #1 on Scene Generation on OSM
1 code implementation • ICCV 2023 • Zhitao Yang, Zhongang Cai, Haiyi Mei, Shuai Liu, Zhaoxi Chen, Weiye Xiao, Yukun Wei, Zhongfei Qing, Chen Wei, Bo Dai, Wayne Wu, Chen Qian, Dahua Lin, Ziwei Liu, Lei Yang
Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets.
1 code implementation • 28 Mar 2023 • Peng Wang, YuAn Liu, Zhaoxi Chen, Lingjie Liu, Ziwei Liu, Taku Komura, Christian Theobalt, Wenping Wang
Based on our analysis, we further propose a novel space-warping method called perspective warping, which allows us to handle arbitrary trajectories in the grid-based NeRF framework.
no code implementations • ICCV 2023 • Guangcong Wang, Zhaoxi Chen, Chen Change Loy, Ziwei Liu
Since coarse depth maps are not strictly scaled to the ground-truth depth maps, we propose a simple yet effective constraint, a local depth ranking method, on NeRFs such that the expected depth ranking of the NeRF is consistent with that of the coarse depth maps in local patches.
1 code implementation • 2 Feb 2023 • Zhaoxi Chen, Guangcong Wang, Ziwei Liu
Our approach begins with an efficient bird's-eye-view (BEV) representation generated from simplex noise, which includes a height field for surface elevation and a semantic field for detailed scene semantics.
Ranked #3 on Scene Generation on GoogleEarth
no code implementations • CVPR 2023 • Peng Wang, YuAn Liu, Zhaoxi Chen, Lingjie Liu, Ziwei Liu, Taku Komura, Christian Theobalt, Wenping Wang
Existing fast grid-based NeRF training frameworks, like Instant-NGP, Plenoxels, DVGO, or TensoRF, are mainly designed for bounded scenes and rely on space warping to handle unbounded scenes.
1 code implementation • 10 Oct 2022 • Fangzhou Hong, Zhaoxi Chen, Yushi Lan, Liang Pan, Ziwei Liu
At the core of EVA3D is a compositional human NeRF representation, which divides the human body into local parts.
1 code implementation • 20 Sep 2022 • Zhaoxi Chen, Guangcong Wang, Ziwei Liu
To achieve super-resolution inverse tone mapping, we derive a continuous representation of 360-degree imaging from the LDR panorama as a set of structured latent codes anchored to the sphere.
1 code implementation • 14 Jul 2022 • Zhaoxi Chen, Ziwei Liu
Our key insight is that the space-time varying geometry and reflectance of the human body can be decomposed as a set of neural fields of normal, occlusion, diffuse, and specular maps.
1 code implementation • ICCV 2021 • Yulin Wang, Zhaoxi Chen, Haojun Jiang, Shiji Song, Yizeng Han, Gao Huang
In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency.
no code implementations • 25 Feb 2021 • Zhuolin Yang, Zhaoxi Chen, Tiffany Cai, Xinyun Chen, Bo Li, Yuandong Tian
Extensive experiments show that student specialization correlates strongly with model robustness in different scenarios, including student trained via standard training, adversarial training, confidence-calibrated adversarial training, and training with robust feature dataset.
no code implementations • 18 Jan 2021 • Zhaoxi Chen, Qing Xu, Ke Zhang, Wing-Han Wong, De-Long Zhang, Edwin Yue-Bun Pun, Cheng Wang
Lithium niobate on insulator (LNOI) is an emerging photonic platform with great promises for future optical communications, nonlinear optics and microwave photonics.
Optics Applied Physics
no code implementations • 17 Dec 2020 • Zhonghan Niu, Zhaoxi Chen, Linyi Li, YuBin Yang, Bo Li, JinFeng Yi
Surprisingly, our experimental results show that even if most of the perturbations in each dimension is eliminated, it is still difficult to obtain satisfactory robustness.