Scholar
Boris Chidlovskii
Google Scholar ID: V7EJdOcAAAAJ
Principal Scientist, Naver Labs Europe
Citations & Impact
Citations
3,377
H-index
26
i10-index
63
Publications
20
Co-authors
21
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including:
- - PanSt3R: Multi-view consistent panoptic segmentation
- - MUSt3R: Multi-view Network for Stereo 3D Reconstruction
- - Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach
- - 3D-consistent image inpainting with diffusion models
- - DUSt3R: Geometric 3D Vision Made Easy
- - Learning to navigate efficiently and precisely in real environments
- - Self-supervised pretraining and finetuning for monocular depth and visual odometry
- - End-to-End (instance)-image goal navigation through correspondence as an emergent phenomenon
- - Zero-BEV: Zero-shot projection of any first-person modality to BEV maps
- - CroCo v2: Improved cross-view completion pre-training for stereo matching and optical flow
- - Learning whom to trust in navigation: dynamically switching between classical and neural planning
- - Multi-Object Navigation in real environments using hybrid policies
- - CroCo: Self-Supervised Pretraining for 3D Vision Tasks by Cross-View Completion
- - Semantic image segmentation: two decades of research
- - PUMP: pyramidal and uniqueness matching priors for unsupervised learning of local features
- - Unsupervised domain adaptation for semantic image segmentation: a comprehensive survey
- - An in-depth experimental study of sensor usage and visual reasoning of robots navigating in real environments
- - Learning synthetic to real transfer for localization and navigational tasks
- - Magnetic field sensing for pedestrian and robot indoor positioning
- - Learning from long-tailed data with noisy labels
- - Universal domain adaptation in ordinal regression
Miscellany
- Telephone number: +33 (0)4 76 61 50 25
- E-mail address: boris.chidlovskii@naverlabs.com
