6 papers
Stable Velocity: A Variance Perspective on Flow Matching
Donglin Yang, Yongxing Zhang, Xin Yu +5
While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By…
Self-Evaluation Unlocks Any-Step Text-to-Image Generation
Xin Yu, Xiaojuan Qi, Zhengqi Li +6
We introduce the Self-Evaluating Model (Self-E), a novel, from-scratch training approach for text-to-image generation that supports any-step inference. Self-E learns from data simi…
LaFiTe: A Generative Latent Field for 3D Native Texturing
Chia-Hao Chen, Zi-Xin Zou, Yan-Pei Cao +6
Generating high-fidelity, seamless textures directly on 3D surfaces, what we term 3D-native texturing, remains a fundamental open challenge, with the potential to overcome long-sta…
SeqTex: Generate Mesh Textures in Video Sequence
Ze Yuan, Xin Yu, Yangtian Sun +4
Training native 3D texture generative models remains a fundamental yet challenging problem, largely due to the limited availability of large-scale, high-quality 3D texture datasets…
UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation
Yang-Tian Sun, Xin Yu, Zehuan Huang +5
Recently, methods leveraging diffusion model priors to assist monocular geometric estimation (e.g., depth and normal) have gained significant attention due to their strong generali…
ObjectMover: Generative Object Movement with Video Prior
Xin Yu, Tianyu Wang, Soo Ye Kim +5
Simple as it seems, moving an object to another location within an image is, in fact, a challenging image-editing task that requires re-harmonizing the lighting, adjusting the pose…