7 papers
Advances in Global Solvers for 3D Vision
Zhenjun Zhao, Heng Yang, Bangyan Liao +7
Global solvers have emerged as a powerful paradigm for 3D vision, offering certifiable solutions to nonconvex geometric optimization problems traditionally addressed by local or he…
scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction
Chenglei Yu, Chuanrui Wang, Bangyan Liao +1
A central goal in systems biology and drug discovery is to predict the transcriptional response of cells to perturbations. This task is challenging due to the noisy and sparse natu…
Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning
Jiayao Mai, Bangyan Liao, Zhenjun Zhao +6
The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-findin…
E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
Wenpu Li, Bangyan Liao, Yi Zhou +3
The estimation of optical flow and 6-DoF ego-motion, two fundamental tasks in 3D vision, has typically been addressed independently. For neuromorphic vision (e.g., event cameras),…
Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World
Bangyan Liao, Zhenjun Zhao, Haoang Li +4
Determining the vanishing points (VPs) in a Manhattan world, as a fundamental task in many 3D vision applications, consists of jointly inferring the line-VP association and locatin…
VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL
Fengyuan Dai, Zifeng Zhuang, Yufei Huang +4
Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. Wh…