Reactive Closed-Loop Computer Vision
The goal of this cluster is to develop machine vision algorithms that can be used in closed-loop and interactive applications extending the capabilities of modern vision systems, which have been transformational for static tasks.
Our group combines the expertise of multiple research labs at Rice University through the Ken Kennedy Institute to advance computer vision. We are especially interested in developing computer vision systems for dynamic and interactive settings where continuous interplay with the environment and adaptation to real-time changes are required. We envision reactive and adaptive computer vision systems, specifically through the implementation of closed-loop systems that can take advantage of continuous feedback from complementary modalities such as sound, speech, temperature, and other environment variables. We envision models that can work in a diverse array of image domains and dynamically adapt to environmental conditions on-the-fly without human intervention in response to both sensor data and detected environment variable changes.
Cluster Members
- Lead PI: Vicente Ordóñez-Román (Computer Science, Rice University)
- Guha Balakrishnan (Electrical & Computer Engineering, Rice University)
- Ashok Veeraraghavan (Electrical & Computer Engineering, Rice University)
Collaborators
- Vivek Boominathan (Electrical & Computer Engineering, Rice University)
-
Selected Publications
-
Cluster faculty highlighted in bold.
- DecentNeRFs: Decentralized Neural Radiance Fields. Zaid Tasneem, Akshat Dave, Abhishek Singh, Kushagra Tiwary, Praneeth Vepakomma, Ashok Veeraraghavan, Ramesh Raskar. European Conference on Computer Vision. ECCV 2024. Milan, Italy. [project page] [arxiv]
- ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders. Jefferson Hernandez, Ruben Villegas, Vicente Ordonez. European Conference on Computer Vision. ECCV 2024. Milan, Italy. [project page] [github] [arxiv]
- Grounding Language Models for Visual Entity Recognition. Zilin Xiao, Ming Gong, Paola Cascante-Bonilla, Xingyao Zhang, Jie Wu, Vicente Ordonez. European Conference on Computer Vision. ECCV 2024. Milan, Italy. [github] [arxiv]
Updates will be posted to the following web page, managed by the cluster: https://vision.rice.edu