- Видео 252
- Просмотров 296 691
Mitsubishi Electric Research Labs (MERL)
США
Добавлен 21 май 2015
[CVPR 2024] Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sa...
[CVPR 2024] Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling
MERL Researcher Moitreya Chatterjee presents his paper titled "Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling" for the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), to be held in Seattle, WA, USA June 17-21, 2024. The paper was co-authored with former MERL intern Xinhang Liu, fellow MERL researchers Suhas Lohit and Pedro Miraldo, and Professors Yu-Wing Tai and Chi-Keung Tang.
Paper: merl.com/publications/TR2024-042,
arxiv.org/abs/2406.03723
Abstract: Extensions of Neural Radiance Fields (NeRFs) to model dynamic scenes have en...
MERL Researcher Moitreya Chatterjee presents his paper titled "Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling" for the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), to be held in Seattle, WA, USA June 17-21, 2024. The paper was co-authored with former MERL intern Xinhang Liu, fellow MERL researchers Suhas Lohit and Pedro Miraldo, and Professors Yu-Wing Tai and Chi-Keung Tang.
Paper: merl.com/publications/TR2024-042,
arxiv.org/abs/2406.03723
Abstract: Extensions of Neural Radiance Fields (NeRFs) to model dynamic scenes have en...
Просмотров: 144
Видео
Decentralized, Safe, Multi-agent Motion Planning for Drones Under Uncertainty via Filtered Reinfo...
Просмотров 642 месяца назад
Decentralized, Safe, Multi-agent Motion Planning for Drones Under Uncertainty via Filtered Reinforcement Learning This video demonstrates our recent work on decentralized, multi-agent motion planning under stochastic uncertainty. Our scalable approach generates safe motion plans in real-time using off-the-shelf, single-agent reinforcement learning rendered safe using distributionally-robust, co...
Graph-Based Invariant Set Planning for Quadrotors
Просмотров 632 месяца назад
We propose a motion planner for quadrotor unmanned aerial vehicles (UAVs) implemented as a graph search over robust positively invariant (PI) sets. We model the positional error dynamics of the quadrotor in closed-loop with an onboard controller as a second-order system, with polytopic uncertainty in the gains under idealized conditions. In addition to this structured uncertainty, we also consi...
![[CVPR 2024] TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models](http://i.ytimg.com/vi/-N5FID-Qs7A/mqdefault.jpg)
[CVPR 2024] TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models
Просмотров 1222 месяца назад
MERL former intern Haomiao Ni presents our paper, "TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models," at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), held in Seattle, Washington June 17-21 2024. The paper was co-authored with MERL researchers Suhas Lohit, Anoop Cherian, Ye Wang, Toshiaki Koike-Akino, and Tim K. Marks, as well as MERL consu...
![[MERL Seminar Series Spring 2024] Neural Certificates and LLMs in Large-Scale Autonomy Design](http://i.ytimg.com/vi/ZBr8g_2_7vw/mqdefault.jpg)
[MERL Seminar Series Spring 2024] Neural Certificates and LLMs in Large-Scale Autonomy Design
Просмотров 682 месяца назад
Chuchu Fan, MIT, presented a talk in the MERL Seminar Series on May 29, 2024. Abstract: Learning-enabled control systems have demonstrated impressive empirical performance on challenging control problems in robotics. However, this performance often arrives with the trade-off of diminished transparency and the absence of guarantees regarding the safety and stability of the learned controllers. I...
![[ACC 2024] Leveraging Computational Fluid Dynamics in UAV Motion Planning](http://i.ytimg.com/vi/AZo-bEB2LYc/mqdefault.jpg)
[ACC 2024] Leveraging Computational Fluid Dynamics in UAV Motion Planning
Просмотров 2653 месяца назад
This video demonstrates the hardware experiments associated with the American Control Conference 2024 paper "Leveraging Computational Fluid Dynamics in UAV Motion Planning", by Yunshen Huang, Marcus Greiff, Abraham Vinod, and Stefano Di Cairano. Corresponding author: abraham.p.vinod@ieee.org. Paper: www.merl.com/publications/TR2024-050 Abstract: We propose a motion planner for quadrotor UAVs in...
![[CVPR 2024] Long-Tailed Anomaly Detection with Learnable Class Names](http://i.ytimg.com/vi/D-2esEYCiPM/mqdefault.jpg)
[CVPR 2024] Long-Tailed Anomaly Detection with Learnable Class Names
Просмотров 4793 месяца назад
MERL Intern Chih-Hui Ho and MERL Researcher Kuan-Chuan Peng present their paper titled "Long-Tailed Anomaly Detection with Learnable Class Names" for the IEEE Computer Vision and Pattern Recognition (CVPR) conference, held in Seattle, WA on June 17-21, 2024. The paper was co-authored with Prof. Nuno Vasconcelos. Paper: www.merl.com/publications/TR2024-040 Abstract: Anomaly detection (AD) aims t...
![[ICASSP XAI-SA 2024] Why does music source separation benefit from cacophony?](http://i.ytimg.com/vi/9L-rjXa6p8E/mqdefault.jpg)
[ICASSP XAI-SA 2024] Why does music source separation benefit from cacophony?
Просмотров 1234 месяца назад
Former MERL Intern Chang-Bin Jeon presents his paper titled "Why does music source separation benefit from cacophony?" for the IEEE ICASSP Satellite Workshop on Explainable Machine Learning for Speech and Audio (XAI-SA), held in Seoul (South Korea) Apr 15 2024. The paper was co-authored with MERL researchers Gordon Wichern, François G. Germain and Jonathan Le Roux. Paper: merl.com/publications/...
![[MERL Seminar Series Spring 2024] Decoding Hidden Worlds: Unprecedented Sensing and Connectivity...](/img/1.gif)
[MERL Seminar Series Spring 2024] Decoding Hidden Worlds: Unprecedented Sensing and Connectivity...
Просмотров 2044 месяца назад
[MERL Seminar Series Spring 2024] Decoding Hidden Worlds: Unprecedented Sensing and Connectivity for Climate, Robotics, & Smart Environments Fadel Adib, MIT & Cartesian, presented a talk in the MERL Seminar Series on April 3, 2024. Abstract: This talk will cover a new generation of technologies that can sense, connect, and perceive the physical world in unprecedented ways. These technologies ca...
Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling
Просмотров 1864 месяца назад
Extensions of Neural Radiance Fields (NeRFs) to model dynamic scenes have enabled their near photo-realistic, free-viewpoint rendering. Although these methods have shown some potential in creating immersive experiences, two drawbacks limit their ubiquity: (i) a significant reduction in reconstruction quality when the computing budget is limited, and (ii) a lack of semantic understanding of the ...
MERL's Quantum AI Technology
Просмотров 1824 месяца назад
Artificial Intelligence (AI) has a widespread impact that changes our world, from everyday living at home to societal evolution at large. A society empowered by AI advancements will elevate your quality of life. AI has also brought the revolution in industrial sectors through transformative solutions and services. Mitsubishi Electric Research Laboratories (MERL) has introduced our cutting-edge ...
Robust In-Hand Manipulation with Extrinsic Contacts
Просмотров 1384 месяца назад
This video describes our new work on robust in-hand manipulation of objects. This work has been accepted for presentation at ICRA 2024. A brief description is provided below. We present in-hand manipulation tasks where a robot moves an object in grasp, maintains its external contact mode with the environment, and adjusts its in-hand pose simultaneously. Unexpected contact mode transition, in th...
[MERL Seminar Series Spring 2024] Are Emergent Abilities of Large Language Models a Mirage?
Просмотров 4484 месяца назад
Sanmi Koyejo, Stanford University, presented a talk in the MERL Seminar Series on March 20, 2024. Abstract: Recent work claims that large language models display emergent abilities, abilities not present in smaller-scale models that are present in larger-scale models. What makes emergent abilities intriguing is two-fold: their sharpness, transitioning seemingly instantaneously from not present ...
[MERL Seminar Series Spring 2024] Enhancing the Efficiency and Robustness of Human-Robot Interaction
Просмотров 615 месяцев назад
[MERL Seminar Series Spring 2024] Enhancing the Efficiency and Robustness of Human-Robot Interactions Stefanos Nikolaidis, University of Southern California, presented a talk in the MERL Seminar Series on March 8, 2024. Abstract: While robots have been successfully deployed in factory floors and warehouses, there has been limited progress in having them perform physical tasks with people at hom...
Autonomous Robotic Assembly
Просмотров 1,5 тыс.5 месяцев назад
MERL introduces a new autonomous robotic assembly technology, offering an initial glimpse into how robots will work in future factories. Unlike conventional approaches where humans set pre-conditions for assembly, our technology empowers robots to adapt to diverse scenarios. We showcase the autonomous assembly of a gear box that was demonstrated live at CES2024. We have developed fundamental te...
[MERL Seminar Series Spring 2024] The Debate Over 'Understanding' in AI's Large Language Models
Просмотров 1376 месяцев назад
[MERL Seminar Series Spring 2024] The Debate Over 'Understanding' in AI's Large Language Models
[MERL Seminar Series Spring 2024] Computational models of human auditory and language processing
Просмотров 2806 месяцев назад
[MERL Seminar Series Spring 2024] Computational models of human auditory and language processing
[ICCV 2023] Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes
Просмотров 1026 месяцев назад
[ICCV 2023] Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes
[WACV 2024] Pixel-Grounded Prototypical Part Networks
Просмотров 1067 месяцев назад
[WACV 2024] Pixel-Grounded Prototypical Part Networks
[GLOBECOM 2022/VCC 2023 Tutorial] Post-Deep Learning Era: Emerging Quantum Machine Learning for ...
Просмотров 917 месяцев назад
[GLOBECOM 2022/VCC 2023 Tutorial] Post-Deep Learning Era: Emerging Quantum Machine Learning for ...
[GLOBECOM 2022/VCC 2023 Tutorial] Post-Deep Learning Era: Emerging Quantum Machine Learning for ...
Просмотров 2667 месяцев назад
[GLOBECOM 2022/VCC 2023 Tutorial] Post-Deep Learning Era: Emerging Quantum Machine Learning for ...
[MERL Seminar Series Fall 2023] Robust and Physics-informed machine learning for low light imaging
Просмотров 1448 месяцев назад
[MERL Seminar Series Fall 2023] Robust and Physics-informed machine learning for low light imaging
Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selection
Просмотров 2678 месяцев назад
Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selection
Large Language Models for Partially Observable Robotic Task Planning
Просмотров 6598 месяцев назад
Large Language Models for Partially Observable Robotic Task Planning
[MERL Seminar Series Fall 2023] Co-Design of Complex Systems: From Autonomy to Future Mobility
Просмотров 1698 месяцев назад
[MERL Seminar Series Fall 2023] Co-Design of Complex Systems: From Autonomy to Future Mobility
[ASRU 2023] Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction
Просмотров 1618 месяцев назад
[ASRU 2023] Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction
[MERL Seminar Series Fall 2023] Visual Programming - A compositional approach to building General...
Просмотров 1779 месяцев назад
[MERL Seminar Series Fall 2023] Visual Programming - A compositional approach to building General...
[MERL Seminar Series Fall 2023] Multiplicity in Machine Learning
Просмотров 1019 месяцев назад
[MERL Seminar Series Fall 2023] Multiplicity in Machine Learning
[ICCV 2021] A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction
Просмотров 709 месяцев назад
[ICCV 2021] A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction
[ICIP 2023] Unrolled-iPPG: Video Heart Rate Estimation via Unrolling Proximal Gradient Descent
Просмотров 1209 месяцев назад
[ICIP 2023] Unrolled-iPPG: Video Heart Rate Estimation via Unrolling Proximal Gradient Descent