9 papers · 1 filter
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…
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…
Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation
Weimin Bai, Yubo Li, Weijian Luo +2
Score Distillation Sampling (SDS) enables high-quality text-to-3D generation by supervising 3D models through the denoising of multi-view 2D renderings, using a pretrained text-to-…
Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching
Weimin Bai, Yubo Li, Wenzheng Chen +2
Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis. However, existing methods typically rely on Score Distillation Sam…