Research
LA-Pose: Latent Action Pretraining Meets Pose Estimation
Z Wang, Saurabh Nair, P Chidananda, P Kachana, S Li, M Brown, Y Furukawa
arXiv 2026 · project page · arXiv
Repurposes latent actions learned self-supervised from driving videos for camera pose estimation, using orders of magnitude less labelled data.
Rig3R: Rig-Aware Conditioning and Discovery for 3D Reconstruction
S Li, P Kachana, P Chidananda, Saurabh Nair, Y Furukawa, M Brown
NeurIPS 2025 · arXiv
Multi-view 3D reconstruction that uses camera-rig structure when it's known and infers it when it isn't, in a single forward pass.
LingoQA: Visual Question Answering for Autonomous Driving
AM Marcu, L Chen, J Hünermann, A Karnsund, B Hanotte, P Chidananda, Saurabh Nair, V Badrinarayanan, A Kendall, J Shotton, E Arani, O Sinavski
A benchmark and dataset for video question answering in driving, with Lingo-Judge, a learned metric that tracks human judgement.
PixTrack: Precise 6DoF Object Pose Tracking using NeRF Templates and Feature-metric Alignment
P Chidananda, Saurabh Nair, D Lee, A Kaehler
arXiv 2022 · arXiv
A Novel Approach for Classification of Normal/Abnormal Phonocardiogram Recordings using Temporal Signal Analysis and Machine Learning
S Vernekar, Saurabh Nair, D Vijaysenan, R Ranjan
Computing in Cardiology (CinC) 2016 · scholar
Development of Autonomous Humanoid Robot Control for a Competitive Environment using Fuzzy Logic and Heuristic Search
R Samant, Saurabh Nair, F Kazi
IFAC-PapersOnLine 2016 · scholar