1 code implementation • 18 Mar 2024 • Gaurav Parmar, Taesung Park, Srinivasa Narasimhan, Jun-Yan Zhu
In this work, we address two limitations of existing conditional diffusion models: their slow inference speed due to the iterative denoising process and their reliance on paired data for model fine-tuning.
no code implementations • 24 Feb 2023 • Siddharth Ancha, Gaurav Pathak, Ji Zhang, Srinivasa Narasimhan, David Held
To navigate in an environment safely and autonomously, robots must accurately estimate where obstacles are and how they move.
no code implementations • CVPR 2021 • N. Dinesh Reddy, Laurent Guigues, Leonid Pischulini, Jayan Eledath, Srinivasa Narasimhan
At the core of our approach is a novel spatio-temporal formulation that operates in a common voxelized feature space aggregated from single- or multiple camera views.
Ranked #1 on 3D Human Pose Estimation on Panoptic (using extra training data)
no code implementations • CVPR 2020 • Aayush Bansal, Minh Vo, Yaser Sheikh, Deva Ramanan, Srinivasa Narasimhan
We present a data-driven approach for 4D space-time visualization of dynamic events from videos captured by hand-held multiple cameras.
1 code implementation • 9 Jan 2019 • Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa Narasimhan, Jan Kautz
Depth sensing is crucial for 3D reconstruction and scene understanding.
no code implementations • 22 May 2018 • Minh Vo, Ersin Yumer, Kalyan Sunkavalli, Sunil Hadap, Yaser Sheikh, Srinivasa Narasimhan
Reliable markerless motion tracking of people participating in a complex group activity from multiple moving cameras is challenging due to frequent occlusions, strong viewpoint and appearance variations, and asynchronous video streams.
no code implementations • CVPR 2015 • Chao Liu, Hernando Gomez, Srinivasa Narasimhan, Artur Dubrawski, Michael R. Pinsky, Brian Zuckerbraun
Our method is able to extract microcirculatory measurements that are consistent with clinical intuition and it has a potential to become a useful tool in critical care medicine.