6 papers
DreamUV: Unwrap Artist-like UV by End-to-End Flow Matching
Quanyuan Ruan, Jiabao Lei, Xingyi Du +1
UV parameterization is a fundamental step in 3D content creation, yet producing production-ready UV layouts remains challenging due to the gap between geometric distortion objectiv…
ARGS: Auto-Regressive Gaussian Splatting via Parallel Progressive Next-Scale Prediction
Quanyuan Ruan, Kewei Shi, Jiabao Lei +2
Auto-regressive frameworks for next-scale prediction of 2D images have demonstrated strong potential for producing diverse and sophisticated content by progressively refining a coa…
ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction
Jiabao Lei, Kewei Shi, Zhihao Liang +1
Directly generating 3D meshes, the default representation for 3D shapes in the graphics industry, using auto-regressive (AR) models has become popular these days, thanks to their s…
SceneLCM: End-to-End Layout-Guided Interactive Indoor Scene Generation with Latent Consistency Model
Yangkai Lin, Jiabao Lei, Kui Jia
Our project page: https://scutyklin.github.io/SceneLCM/. Automated generation of complex, interactive indoor scenes tailored to user prompt remains a formidable challenge. While ex…
Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Styles
Yangkai Lin, Jiabao Lei, Kui jia
In recent years, there has been a growing demand to stylize a given 3D scene to align with the artistic style of reference images for creative purposes. While 3D Gaussian Splatting…
Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions
Quanyuan Ruan, Jiabao Lei, Wenhao Yuan +4
Differentiable rendering has gained significant attention in the field of robotics, with differentiable robot rendering emerging as an effective paradigm for learning robotic actio…