Yinghao Xu

Yinghao Xu

Auto-generated profile, based on publicly available information

Yinghao Xu

Stanford University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 November 2024
Verified
Book Chapter
Closed access
PDF file
YXYinghao Xu
Yinghao Xu
ZSZifan Shi
Zifan Shi
WYWang Yifan
Wang Yifan
HCHansheng Chen
Hansheng Chen
CYCeyuan Yang
Ceyuan Yang
GWGordon Wetzstein
Gordon Wetzstein

22 October 2022
Verified
Book Chapter
Closed access
PDF file
XLXian Liu
Xian Liu
YXYinghao Xu
Yinghao Xu
QWQianyi Wu
Qianyi Wu
HZHang Zhou
Hang Zhou
WWWayne Wu
Wayne Wu
BZBolei Zhou
Bolei Zhou

19 November 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
ZXZhen Xu
Zhen Xu
YXYinghao Xu
Yinghao Xu
ZYZhiyuan Yu
Zhiyuan Yu
SPSida Peng
Sida Peng
JSJiaming Sun
Jiaming Sun
XZXiaowei Zhou
Xiaowei Zhou
This paper aims to address the challenge of reconstructing long volumetric videos from multi-view RGB videos. Recent dynamic view synthesis methods leverage powerful 4D representations, like feature grids or point cloud sequences, to achieve high-quality rendering results. However, they are typically limited to short (1~2s) video clips and often suffer from large memory footprints when dealing with longer videos. To solve this issue, we propose a novel 4D representation, named Temporal Gaussian Hierarchy, to compactly model long volumetric videos. Our key observation is that there are generally various degrees of temporal redundancy in dynamic scenes, which consist of areas changing at different speeds. Motivated by this, our approach builds a multi-level hierarchy of 4D Gaussian primitives, where each level separately describes scene regions with different degrees of content change, and adaptively shares Gaussian primitives to represent unchanged scene content over different temporal segments, thus effectively reducing the number of Gaussian primitives. In addition, the tree-like structure of the Gaussian hierarchy allows us to efficiently represent the scene at a particular moment with a subset of Gaussian primitives, leading to nearly constant GPU memory usage during the training or rendering regardless of the video length. Moreover, we design a Compact Appearance Model that mixes diffuse and view-dependent Gaussians to further minimize the model size while maintaining the rendering quality. We also develop a rasterization pipeline of Gaussian primitives based on the hardware-accelerated technique to improve rendering speed. Extensive experimental results demonstrate the superiority of our method over alternative methods in terms of training cost, rendering speed, and storage usage. To our knowledge, this work is the first approach capable of efficiently handling hours of volumetric video data while maintaining state-of-the-art rendering quality.

16 February 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SPSida Peng
Sida Peng
CGChen Geng
Chen Geng
YZYuanqing Zhang
Yuanqing Zhang
YXYinghao Xu
Yinghao Xu
QWQianqian Wang
Qianqian Wang
HBHujun Bao
Hujun Bao
This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views. Some recent works have shown that learning implicit neural representations of 3D scenes achieves remarkable view synthesis quality given dense input views. However, the representation learning will be ill-posed if the views are highly sparse. To solve this ill-posed problem, our key idea is to integrate observations over video frames. To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh, so that the observations across frames can be naturally integrated. The deformable mesh also provides geometric guidance for the network to learn 3D representations more efficiently. Furthermore, we combine Neural Body with implicit surface models to improve the learned geometry. To evaluate our approach, we perform experiments on both synthetic and real-world data, which show that our approach outperforms prior works by a large margin on novel view synthesis and 3D reconstruction. We also demonstrate the capability of our approach to reconstruct a moving person from a monocular video on the People-Snapshot dataset.

1 February 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JZJiapeng Zhu
Jiapeng Zhu
YSYujun Shen
Yujun Shen
YXYinghao Xu
Yinghao Xu
DZDeli Zhao
Deli Zhao
QCQifeng Chen
Qifeng Chen
BZBolei Zhou
Bolei Zhou
Generative Adversarial Networks (GANs) have significantly advanced image synthesis through mapping randomly sampled latent codes to high-fidelity synthesized images. However, applying well-trained GANs to real image editing remains challenging. A common solution is to find an approximate latent code that can adequately recover the input image to edit, which is also known as GAN inversion. To invert a GAN model, prior works typically focus on reconstructing the target image at the pixel level, yet few studies are conducted on whether the inverted result can well support manipulation at the semantic level. This work fills in this gap by proposing in-domain GAN inversion , which consists of a domain-guided encoder and a domain-regularized optimizer , to regularize the inverted code in the native latent space of the pre-trained GAN model. In this way, we manage to sufficiently reuse the knowledge learned by GANs for image reconstruction, facilitating a wide range of editing applications without any retraining. We further make comprehensive analyses on the effects of the encoder structure, the starting inversion point, as well as the inversion parameter space, and observe the trade-off between the reconstruction quality and the editing property. Such a trade-off sheds light on how a GAN model represents an image with various semantics encoded in the learned latent distribution.

27 July 2025 in ACM Transactions on Graphics
Verified
Journal Article
Open access
RSRuizhi Shao
Ruizhi Shao
YXYinghao Xu
Yinghao Xu
YSYujun Shen
Yujun Shen
CYCeyuan Yang
Ceyuan Yang
YZYang Zheng
Yang Zheng
GWGordon Wetzstein
Gordon Wetzstein
Generating photorealistic videos of digital humans in a controllable manner is crucial for a plethora of applications. Existing approaches either build on methods that employ template-based 3D representations or emerging video generation models but suffer from poor quality or limited consistency and identity preservation when generating individual or multiple digital humans. In this paper, we introduce a new interspatial attention (ISA) mechanism as a scalable building block for modern diffusion transformer (DiT)-based video generation models. ISA is a new type of cross attention that uses relative positional encodings tailored for the generation of human videos. Leveraging a custom-developed video variation autoencoder, we train a latent ISA-based diffusion model on a large corpus of video data. Our model achieves state-of-the-art performance for 4D human video synthesis, demonstrating remarkable motion consistency and identity preservation while providing precise control of the camera and body poses. Our code and model are publicly released at https://dsaurus.github.io/isa4d/.