PPaperPicks

Mathieu Salzmann

28 papers at tracked venues · 20 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation
  2. Demystifying Singular Defects in Large Language Models
  3. Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds
  4. Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera
  5. GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
  6. Leveraging Gradient Information for Out-of-Domain Performance Estimations
  7. MotionMap: Representing Multimodality in Human Pose Forecasting
  8. QT-DoG: Quantization-Aware Training for Domain Generalization
  9. Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis
  10. Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression
  11. 3D Single-Object Tracking in Point Clouds with High Temporal Variation
  12. 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
  13. AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains
  14. CLOAF: CoLlisiOn-Aware Human Flow
  15. DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses
  16. Data Augmentation via Latent Diffusion for Saliency Prediction
  17. Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
  18. GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence
  19. HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields
  20. LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields
  21. Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning
  22. Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning Through Object Exchange
  23. NOPE: Novel Object Pose Estimation from a Single Image
  24. Neural SDF Flow for 3D Reconstruction of Dynamic Scenes
  25. SINDER: Repairing the Singular Defects of DINOv2
  26. Source-Free Domain-Invariant Performance Prediction
  27. TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression
  28. Unlocking Comics: The AI4VA Dataset for Visual Understanding