Zhenzhang Ye
YOU?
Author Swipe
View article: Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction Open
Probabilistic human motion prediction aims to forecast multiple possible future movements from past observations. While current approaches report high diversity and realism, they often generate motions with undetected limb stretching and j…
View article: Sparse Views, Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo
Sparse Views, Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo Open
Neural approaches have shown a significant progress on camera-based reconstruction. But they require either a fairly dense sampling of the viewing sphere, or pre-training on an existing dataset, thereby limiting their generalizability. In …
View article: Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization Open
Bilevel optimization aims to optimize an outer objective function that depends on the solution to an inner optimization problem. It is routinely used in Machine Learning, notably for hyperparameter tuning. The conventional method to comput…
View article: A Cutting-Plane Method for Sublabel-Accurate Relaxation of Problems with Product Label Spaces
A Cutting-Plane Method for Sublabel-Accurate Relaxation of Problems with Product Label Spaces Open
View article: Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections
Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections Open
Graph matching aims to establish correspondences between vertices of graphs such that both the node and edge attributes agree. Various learning-based methods were recently proposed for finding correspondences between image key points based…
View article: Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections
Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections Open
Graph matching aims to establish correspondences between vertices of graphs such that both the node and edge attributes agree. Various learning-based methods were recently proposed for finding correspondences between image key points based…
View article: Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning
Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning Open
Structured convex optimization on weighted graphs finds numerous applications in machine learning and computer vision. In this work, we propose a novel adaptive preconditioning strategy for proximal algorithms on this problem class. Our pr…
View article: Variational Uncalibrated Photometric Stereo Under General Lighting
Variational Uncalibrated Photometric Stereo Under General Lighting Open
Photometric stereo (PS) techniques nowadays remain constrained to an ideal laboratory setup where modeling and calibration of lighting is amenable. To eliminate such restrictions, we propose an efficient principled variational approach to …
View article: Combinatorial Preconditioners for Proximal Algorithms on Graphs
Combinatorial Preconditioners for Proximal Algorithms on Graphs Open
We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners. Such combinatorial preconditioners arise from partitioning the graph into forests. We pr…
View article: Combinatorial Preconditioners for Proximal Algorithms on Graphs
Combinatorial Preconditioners for Proximal Algorithms on Graphs Open
We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners. Such combinatorial preconditioners arise from partitioning the graph into forests. We pr…
View article: Determining the maximum time horizon for vehicles to safely follow a trajectory
Determining the maximum time horizon for vehicles to safely follow a trajectory Open
Dealing with the unknown future behavior of other traffic participants is one of the main challenges when generating safe trajectories for autonomous vehicles. When the ego vehicle (i.e., the vehicle to be controlled) follows a given traje…