Vincent Lepetit

43

Papers

180

Total Citations

Papers (43)

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

NOPE: Novel Object Pose Estimation from a Single Image

Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

NextBestPath: Efficient 3D Mapping of Unseen Environments

Learning to Assign Orientations to Feature Points

Direct Prediction of 3D Body Poses From Motion Compensated Sequences

Efficiently Creating 3D Training Data for Fine Hand Pose Estimation

Learning to Align Semantic Segmentation and 2.5D Maps for Geolocalization

Learning to Find Good Correspondences

3D Pose Estimation and 3D Model Retrieval for Objects in the Wild

Feature Mapping for Learning Fast and Accurate 3D Pose Inference From Synthetic Images

Geometry-Aware Network for Non-Rigid Shape Prediction From a Single View

Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras

HOnnotate: A Method for 3D Annotation of Hand and Object Poses

Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields

Single Image Depth Prediction With Wavelet Decomposition

Monte Carlo Scene Search for 3D Scene Understanding

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation

Back to the Feature: Learning Robust Camera Localization From Pixels To Pose

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation

In-Hand 3D Object Scanning From an RGB Sequence

MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision

Projection Onto the Manifold of Elongated Structures for Accurate Extraction

An Efficient Minimal Solution for Multi-Camera Motion

Training a Feedback Loop for Hand Pose Estimation

A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images

Correspondences of the Third Kind: Camera Pose Estimation from Object Reflection

GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild

Learning To Better Segment Objects From Unseen Classes With Unlabeled Videos

MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans

You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation

S2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching

General 3D Room Layout from a Single View by Render-and-Compare

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud

BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects Without Using Depth

SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

Learning Descriptors for Object Recognition and 3D Pose Estimation

Flying Objects Detection From a Single Moving Camera

TILDE: A Temporally Invariant Learned DEtector

SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration