activity
20242026
collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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-…

cs.CV2025

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…