Maks Ovsjanikov

37

Papers

13

Total Citations

Papers (37)

Memory-Scalable and Simplified Functional Map Learning

Self-Supervised Dual Contouring

Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces

SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications

ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Models

To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning

Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features

PoNQ: a Neural QEM-based Mesh Representation

Isospectralization, or How to Hear Shape, Style, and Correspondence

Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence

ArtEmis: Affective Language for Visual Art

Learning Delaunay Surface Elements for Mesh Reconstruction

Physically-Aware Generative Network for 3D Shape Modeling

Fast Sinkhorn Filters: Using Matrix Scaling for Non-Rigid Shape Correspondence With Functional Maps

Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching

Physical Simulation Layer for Accurate 3D Modeling

Understanding and Improving Features Learned in Deep Functional Maps

Generalizable Local Feature Pre-Training for Deformable Shape Analysis

Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering

Unsupervised Deep Learning for Structured Shape Matching

OperatorNet: Recovering 3D Shapes From Difference Operators

DWKS: A Local Descriptor of Deformations Between Meshes and Point Clouds

Spatially and Spectrally Consistent Deep Functional Maps

VoroMesh: Learning Watertight Surface Meshes with Voronoi Diagrams

SATR: Zero-Shot Semantic Segmentation of 3D Shapes

Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation

PointTriNet: Learned Triangulation of 3D Point Sets

Implicit Field Supervision for Robust Non-rigid Shape Matching

Affection: Learning Affective Explanations for Real-World Visual Data

DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matching

LACONIC: A 3D Layout Adapter for Controllable Image Creation

Correspondence learning via linearly-invariant embedding

Weakly Supervised Deep Functional Maps for Shape Matching

Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching

NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching

Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape Matching

Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction