Mitsubishi Electric Research Laboratories (MERL)

cocktail-fork-separation

Baseline multi-resolution cross network model trained using the Divide and Remaster Dataset

hyper-unmix

Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation.”

BANSAC

A dynamic BAyesian Network for adaptive SAmple Consensus

neural-IIR-field

Neural IIR Filter Field for HRTF Upsampling and Personalization

MotionNet

Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps

SMART

Training and testing code from our CVPR 2023 paper "Are Deep Neural Networks SMARTer than Second Graders?"

PixPNet

Contains code for our paper, Pixel-Grounded Prototypical Part Networks

avlen

Code used in our NeurIPS 2022 paper 'AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments'

1bCRB

One-Bit CRB for estimating angular-domain channel parameters for massive MIMO

Sound2Sight

Generating Visual Dynamics from Sound and Context for generating video frames and their motion dynamics conditioned on audio and a few past frames

AVSGS

Audio Visual Scene-Graph Segmentor

DeepBornFNO

Code for training and using the Born Fourier Neural Operator (BornFNO) model proposed in our ICASSP 2023 paper

MC-PILCO

Monte Carlo Probabilistic Inference for Learning COntrol for modeling and control of dynamical systems

ROSETA

Robust Online Subspace Estimation and Tracking Algorithm for identifying and tracking a time-varying low dimensional subspace

AdvConOT

Representation Learning via Adversarially-Contrastive Optimal Transport

EBAD

Exemplar-Based Anomaly Detection for detecting anomalies in time series

OFENet

Online Feature Extractor Network

PQP

Parallel Quadratic Programming for solving problems involving convex optimization

RIDE

Robust Iterative Data Estimation for white-box adversarial defense via self-supervised data estimation

TEAQC

Template Embeddings for Adiabatic Quantum Computation (TEAQC) for searching for an embedding of a problem graph into certain classes of minors of the Quantum Annealing hardware

CASENet

C++/Python implementation of our CASENet based on Caffe for multi-label semantic edge detection training/testing

CAZSL

Context-Aware Zero Shot Learning

CISOR

Convergent Inverse Scattering using Optimization and Regularization for a systematic comparison between CISOR, SEAGLE, and other state-of-the-art methods on simulated data

CME

Circular Maze Environment

FoldingNet_Plus

For unsupervised learning of 3D point clouds with data-adaptive graph prior

PCQM

Point Cloud Quality Metric for measuring the geometry distortion of point cloud compression

QNTRPO

Quasi-Newton Trust Region Policy Optimization

robust-rotation-estimation

Robust frame-to-frame camera rotation estimation in crowded scenes

SafetyRL

Goal directed RL with Safety Constraints

tssep