Leonid Antsfeld
8 papers · 2022–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (24) 🧭 Keyword Pioneer
🌈
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Deep Learning
(5)
Artificial Intelligence
(4)
Computer Vision
(4)
Machine Learning
(4)
Analysis
(4)
Core AI
(4)
Learning Types · Machine Learning
(3)
Reinforcement Learning
(2)
Robotics
(2)
Applications · Reinforcement Learning
(2)
Capabilities
(2)
Learning Types · Deep Learning
(2)
Techniques
(2)
Computer Science
(1)
Applications · Robotics
(1)
Keywords
3d reconstruction
(2)
embodied ai
(2)
representation learning
(2)
robot navigation
(2)
depth estimation
(2)
visual navigation
(2)
masked image modeling
(2)
vision transformer
(2)
3d scene understanding
(1)
structure from motion
(1)
sim-to-real transfer
(1)
self-supervised learning
(1)
optical flow estimation
(1)
sequential decision making
(1)
stereo matching
(1)
scene understanding
(1)
visual slam
(1)
optical flow
(1)
transfer learning
(1)
semantic segmentation
(1)
Papers
MUSt3R: Multi-view Network for Stereo 3D Reconstruction
CVPR 2025
PanSt3R: Multi-view Consistent Panoptic Segmentation
ICCV 2025
Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach
CVPR 2025
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
ICLR 2024
Learning to Navigate Efficiently and Precisely in Real Environments
CVPR 2024
Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction
ICLR 2024
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow
ICCV 2023
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
NeurIPS 2022