8 papers
Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation
Weimin Bai, Yubo Li, Weijian Luo +4
Text-to-3D generation has advanced rapidly, yet state-of-the-art models, encompassing both optimization-based and feed-forward architectures, still face two fundamental limitations…
An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
Weimin Bai, Yifei Wang, Wenzheng Chen +1
Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits…
RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing
Yiming Shao, Qiyu Dai, Chong Gao +6
Novel view synthesis (NVS) through non-planar refractive surfaces presents fundamental challenges due to severe, spatially varying optical distortions. While recent representations…
Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning
Yuxuan Gu, Weimin Bai, Yifei Wang +2
Masked auto-regressive diffusion models (MAR) benefit from the expressive modeling ability of diffusion models and the flexibility of masked auto-regressive ordering. However, vani…
InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior
Weimin Bai, Suzhe Xu, Yiwei Ren +4
Video inverse problems are fundamental to streaming, telepresence, and AR/VR, where high perceptual quality must coexist with tight latency constraints. Diffusion-based priors curr…
Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
Yifei Wang, Weimin Bai, Colin Zhang +3
In this paper, we unify more than 10 existing one-step diffusion distillation approaches, such as Diff-Instruct, DMD, SIM, SiD, -distill, etc, inside a theory-driven framework w…