Ying-Tian Liu

Ying-Tian Liu

Auto-generated profile, based on publicly available information

Ying-Tian Liu

VAST, Beijing, China

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
19 November 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
XYXin Yu
Xin Yu
ZYZe Yuan
Ze Yuan
YGYuan-Chen Guo
Yuan-Chen Guo
YLYing-Tian Liu
Ying-Tian Liu
JLJianhui Liu
Jianhui Liu
XQXiaojuan Qi
Xiaojuan Qi
While high-quality texture maps are essential for realistic 3D asset rendering, few studies have explored learning directly in the texture space, especially on large-scale datasets. In this work, we depart from the conventional approach of relying on pre-trained 2D diffusion models for testtime optimization of 3D textures. Instead, we focus on the fundamental problem of learning in the UV texture space itself. For the first time, we train a large diffusion model capable of directly generating high-resolution texture maps in a feed-forward manner. To facilitate efficient learning in high-resolution UV spaces, we propose a scalable network architecture that interleaves convolutions on UV maps with attention layers on point clouds. Leveraging this architectural design, we train a 700 million parameter diffusion model that can generate UV texture maps guided by text prompts and single-view images. Once trained, our model naturally supports various extended applications, including text-guided texture inpainting, sparse-view texture completion, and text-driven texture synthesis. The code is available at https://github.com/CVMI-Lab/TEXGen.

14 December 2025
Verified
Conference Paper
Open access
YYYunhan Yang
Yunhan Yang
YZYufan Zhou
Yufan Zhou
YGYuan-Chen Guo
Yuan-Chen Guo
ZZZi-Xin Zou
Zi-Xin Zou
YHYukun Huang
Yukun Huang
XLXihui Liu
Xihui Liu

16 June 2022 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YLYing-Tian Liu
Ying-Tian Liu
YGYuan-Chen Guo
Yuan-Chen Guo
YLYi-Xiao Li
Yi-Xiao Li
CWChen Wang
Chen Wang
SZSong-Hai Zhang
Song-Hai Zhang
Automatic generation of fonts can greatly facilitate the font design process, and provide prototypes where designers can draw inspiration from. Existing generation methods are mainly built upon rasterized glyph images to utilize the successful convolutional architecture, but ignore the vector nature of glyph shapes. We present an implicit representation, modeling each glyph as shape primitives enclosed by several quadratic curves. This structured implicit representation is shown to be better suited for glyph modeling, and enables rendering glyph images at arbitrary high resolutions. Our representation gives high-quality glyph reconstruction and interpolation results, and performs well on the challenging one-shot font style transfer task comparing to other alternatives both qualitatively and quantitatively.

28 October 2024
Verified
Conference Paper
Open access
GLGuan Luo
Guan Luo
TXTian-Xing Xu
Tian-Xing Xu
YLYing-Tian Liu
Ying-Tian Liu
XFXiao-Xiong Fan
Xiao-Xiong Fan
FZFanglue Zhang
Fanglue Zhang
SZSong-Hai Zhang
Song-Hai Zhang
The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D meshes, they often require accurately reconstructed meshes to perform editing, which limits their application in 3D content generation. To address this gap, we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene. To capture long-range object deformation, we introduce positional loss into the optimization process of 3D Gaussian Splatting and enable gradient propagation through reparameterization. To handle occluded 3D Gaussians when rendering from the specified viewpoint, we build an anchor-based structure and employ a coarse-to-fine optimization strategy capable of handling long-range deformation while maintaining structural stability. Furthermore, we design a novel masking strategy to adaptively identify non-rigid deformation regions for fine-scale modeling. Extensive experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation, demonstrating superior editing flexibility and quality compared to previous approaches.

14 December 2025
Verified
Conference Paper
Open access
HXHao Xu
Hao Xu
YZYuqing Zhang
Yuqing Zhang
YWYiqian Wu
Yiqian Wu
XZXinyang Zheng
Xinyang Zheng
YLYutao Liu
Yutao Liu
XJXiaogang Jin
Xiaogang Jin

3 July 2026 in ACM Transactions on Graphics
Verified
Journal Article
Open access
HWHanxiao Wang
Hanxiao Wang
YLYing-Tian Liu
Ying-Tian Liu
YGYuan-Chen Guo
Yuan-Chen Guo
QFQi-Yuan Feng
Qi-Yuan Feng
ZZZi-Xin Zou
Zi-Xin Zou
YCYan-Pei Cao
Yan-Pei Cao
Generating high-quality triangle meshes is essential for film, gaming, and interactive 3D applications. Mainstream methods rely on mesh serialization and autoregressive processes, which stuggles in effective inference and is sensitive to error accumulation. In this paper, we present Nexus , a diffusion method that achieves holistic mesh generation via decoupled vertex and topology generation. First, we view mesh vertices as sparse voxels organized as an octree and adopt a diffusion model to generate the vertices in a coarse-to-fine manner. Second, for topology modeling, we propose Space-time Interval , as an extension of Spacetime Distance to encode arbitrary edge and face topology into continuous per-vertex embeddings. It allows for a global and efficient recovery of complex topology. We then employ a diffusion model to generate the continuous embeddings on the generated vertices. Extensive experiments on the Objaverse and Toys4K datasets and in-the-wild images demonstrate that our method outperforms state-of-the-art autoregressive and two-stage baselines, effectively circumventing the inherent limitations of sequential mesh modeling. A blind user study from 3D practitioners confirms strong perceptual preference for our results.