no code implementations • CVPR 2022 • Ziad Al-Halah, Santhosh K. Ramakrishnan, Kristen Grauman
In reinforcement learning for visual navigation, it is common to develop a model for each new task, and train that model from scratch with task-specific interactions in 3D environments.
2 code implementations • 16 Sep 2021 • Santhosh K. Ramakrishnan, Aaron Gokaslan, Erik Wijmans, Oleksandr Maksymets, Alex Clegg, John Turner, Eric Undersander, Wojciech Galuba, Andrew Westbury, Angel X. Chang, Manolis Savva, Yili Zhao, Dhruv Batra
When compared to existing photorealistic 3D datasets such as Replica, MP3D, Gibson, and ScanNet, images rendered from HM3D have 20 - 85% higher visual fidelity w. r. t.
no code implementations • 3 Feb 2021 • Santhosh K. Ramakrishnan, Tushar Nagarajan, Ziad Al-Halah, Kristen Grauman
We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents.
1 code implementation • ECCV 2020 • Santhosh K. Ramakrishnan, Ziad Al-Halah, Kristen Grauman
State-of-the-art navigation methods leverage a spatial memory to generalize to new environments, but their occupancy maps are limited to capturing the geometric structures directly observed by the agent.
Ranked #3 on Robot Navigation on Habitat 2020 Point Nav test-std
1 code implementation • 7 Jan 2020 • Santhosh K. Ramakrishnan, Dinesh Jayaraman, Kristen Grauman
Embodied computer vision considers perception for robots in novel, unstructured environments.
1 code implementation • Science Robotics 2019 • Santhosh K. Ramakrishnan, Dinesh Jayaraman, Kristen Grauman
Standard computer vision systems assume access to intelligently captured inputs (e. g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself.
no code implementations • ECCV 2018 • Santhosh K. Ramakrishnan, Kristen Grauman
We consider an active visual exploration scenario, where an agent must intelligently select its camera motions to efficiently reconstruct the full environment from only a limited set of narrow field-of-view glimpses.
no code implementations • 7 Jun 2017 • Santhosh K. Ramakrishnan, Swarna Kamlam Ravindran, Anurag Mittal
Experiments show improvements over a simple re-detect-and-match framework as well as KLT in terms of speed/accuracy on different real-world applications, especially at the object boundaries.
no code implementations • CVPR 2017 • Santhosh K. Ramakrishnan, Ambar Pal, Gaurav Sharma, Anurag Mittal
We study the problem of answering questions about images in the harder setting, where the test questions and corresponding images contain novel objects, which were not queried about in the training data.