Mitsubishi Electric Research Laboratories

PS-NeuS: A Probability-guided Sampler for Neural Implicit Surface Rendering: For more accurate and detailed 3D reconstructions and improved image rendering, especially for the regions of interest in a scene.

Several variants of Neural Radiance Fields (NeRFs) have significantly improved the accuracy of image synthesis and surface reconstruction of 3D scenes/objects. A key characteristic of these methods is that they cannot afford to train the neural network using every possible input, specifically, every pixel and every 3D point along each pixel’s projection ray. While vanilla NeRFs uniformly sample both the image pixels and the 3D points along the projection rays, some variants guide the sampling of the 3D points along the projection rays. In this paper, we propose a guided sampling of both the image pixels and the 3D points along the rays. We leverage the implicit surface representation of the foreground scene to model a probability density . . . [learn more]

Learn More about MERL Research

Applied Physics

From first-principles modeling to device designs.

Artificial Intelligence

Making machines smarter for improved safety, efficiency and comfort.

Communications

Wireless and optical communications.

Computational Sensing

Utilizing computation to improve sensing capabilities.

Computer Vision

Extracting meaning and building representations of visual objects and events in the world.

Control

If it moves, we control it.

Data Analytics

Learning from data for optimal decisions.

Dynamical Systems

Exploiting nonlinearity and shaping dynamics in creative and deeply mathematical ways.

Electric Systems

Modeling & optimization of power systems and electromagnetic machines.

Electronic and Photonic Devices

Pursuing theoretical and experimental research for next generation devices.

Machine Learning

Data-driven approaches to design intelligent algorithms.

Multi-Physical Modeling

Optimal design & robust control through multi-physical modeling.

Optimization

Efficient solutions to large-scale problems.

Robotics

Where hardware, software and machine intelligence come together.

Signal Processing

Acquisition and processing of information.

Speech & Audio

Audio source separation, recognition, and understanding.

Mitsubishi Electric Research Laboratories (MERL) is Mitsubishi Electric Corporation's North American research organization.

PS-NeuS: A Probability-guided Sampler for Neural Implicit Surface Rendering: For more accurate and detailed 3D reconstructions and improved image rendering, especially for the regions of interest in a scene.

Internship Openings

Employment Openings

Postdoctoral Research Fellow

Visiting Faculty