Mathieu Salzmann

15

Papers

235

Total Citations

Papers (15)

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

GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control

NOPE: Novel Object Pose Estimation from a Single Image

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

SINDER: Repairing the Singular Defects of DINOv2

Data Augmentation via Latent Diffusion for Saliency Prediction

QT-DoG: Quantization-Aware Training for Domain Generalization

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Density

TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression

Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera

DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

MotionMap: Representing Multimodality in Human Pose Forecasting

CLOAF: CoLlisiOn-Aware Human Flow