Mallesh Dasari's Personal Homepage

Mallesham Dasari

Assistant Professor
Institute for the Wireless Internet of Things
Department of Electrical and Computer Engineering
Northeastern University

Office: 650D EXP
Address: 360 Huntington Ave, Boston, MA 02115
Email: m.dasari@northeastern.edu

Research Interests: Augmented and Virtual Reality (AR/VR) Systems, Computer Networks, Wireless Sensing and Communications, Mobile and Wearable Computing

Recent and Selected Publications

Fumos: Neural Compression and Progressive Refinement for Continuous Point Cloud Video Streaming
IEEE VR 2024 (Conference on Virtual Reality and 3D User Interfaces) - selected to appear in IEEE Transactions on Visualization and Computer Graphics (TVCG)
Paper Video

StageAR: Markerless Mobile Phone Localization for AR in Live Events
IEEE VR 2024 (Conference on Virtual Reality and 3D User Interfaces)
Paper Teaser

MeshReduce: Scalable and Bandwidth Efficient Scene Capture for 3D Telepresence
IEEE VR 2024 (Conference on Virtual Reality and 3D User Interfaces)
Paper Teaser

Scaling VR Video Conferencing
IEEE VR 2023 (Conference on Virtual Reality and 3D User Interfaces)
Paper Slides Code Teaser

RenderFusion: Balancing Local and Remote Rendering for Interactive 3D Scenes
IEEE ISMAR 2023 (Conference on Augmented and Mixed Reality)
Paper Slides Code Teaser

RoVaR: Robust Multi-agent Tracking through Dual-layer Diversity in Visual and RF Sensing
ACM IMWUT/UbiComp 2023 (Conference on Interactive, Mobile, Wearable and Ubiquitous Technologies)
Paper Data AR Game

Hyper-local Conversational Agents for Serving Spatio-temporal Events of a Neighbourhood
ACM IMWUT/UbiComp 2022 (Conference on Interactive, Mobile, Wearable and Ubiquitous Technologies)
Paper

Swift: Adaptive Video Streaming with Layered Neural Codecs
USENIX NSDI 2022 (Conference on Networked Systems Design and Implementation)
Paper Slides Code Video

Cyclops: An FSO-based Wireless Link for VR Headsets
ACM SIGCOMM 2022 (Conference on Data Communications)
Paper

PARSEC: Streaming 360-Degree Videos Using Super-Resolution
IEEE INFOCOM 2020 (Conference on Computer Communications)
Paper Slides Code Video

Impact of Device Performance on Mobile Internet QoE
ACM IMC 2018 (Conference on Internet Measurements)
Paper Slides Data Video

A full list of papers can be found here!

Active Research Projects

Designing Networked Systems for Immersive Experiences

The Internet has seen a remarkable change in long distance communication in terms of voice and video calls in just three decades. However, despite the past advances, today's applications (e.g., Zoom/FaceTime) still lack the essential subtleties of ``Telepresence'' i.e., everyday face-to-face co-located communication with realistic eye contact, body language, and physical presence in a virtual space. While the concept has been around for decades, only recent advances in high performance graphics hardware, better depth sensing technology, and faster software pipelines have made it possible to consider practical real-time 3D telepresence systems. This project investigates several research questions— 1) How to capture and digitize a 3D scene with low latency and practical bitrates to stream on the Internet in real-time? 2) Can the traditional 2D content distribution strategies work well for 3D streaming? 3) How to render high quality 3D content on constrained AR/VR headsets? 4) What kind of 3D applications can we envision to bring the everyday serendipity virtually?

Publications: IEEE VR 2024, IEEE VR 2023, IEEE ISMAR 2023, ACM SIGCOMM 2022

AI Powered Compression and Content Delivery

Video compression plays a central role for Internet video applications in reducing the network bandwidth requirement. Traditional algorithm-driven compression methods have served well to realize today's Internet video applications with an acceptable user experience. However, emerging 4K/8K/360-Degree video streaming, and AR/VR applications require orders of magnitude more bandwidth than today's applications. The monolithic, application-unware nature of the current generation compression algorithms is not scalable to realize such nearfuture applications over the Internet. This project explores data-driven techniques to significantly change the landscape of the source compression algorithms and improve the experience of next-generation video applications.

Publications: IEEE VR 2024, USENIX NSDI 2022, IEEE INFOCOM 2020

Wireless Systems for AR/VR Applications

The interactive and immersive applications such as Augmented Reality (AR) and Virtual Reality (VR) have significant potential for various tasks like industrial training, collaborative robotics, remote operation, etc. A key challenge to deliver these applications is to provide accurate and robust tracking of multiple agents (humans and robots) involved in every-day, challenging environments. Current AR/VR solutions rely on visual tracking algorithms (e.g., SLAM/Odometry) that are highly sensitive to environment (e.g., lighting conditions). This project explores augmenting the RF-positioning (e.g., WiFi/UWB) to improve the tracking in terms of accuracy (< 1cm level), robustness (with diverse environmental conditions), and scalability across multiple agents. The key challenges here are how to leverage two completely different modalities to complement with each other with little or no infrastructure support.

Publications: IEEE VR 2024, ACM IMWUT/UbiComp 2023

Teaching

EECE 5698: Networked XR Systems, Fall 2024, Northeastern University

This is an interdisciplinary course covering the following topics from emerging multimedia, computer networks, vision and graphics. In addition to the regular lectures, the class will also have experiential sessions with a vareity of state-of-the-art XR headsets in the market.

Fundamental problems of networked applications
XR content representations
2D, Flat 360, 3D/Volumetric videos (RGB-D, point cloud, mesh, NeRF)
Monocular, stereoscopic, and multiview videos
Acquiring XR content for network delivery
Compression algorithms for RGB, depth videos, point clouds, mesh sequences
Multiview compression algorithms
Streaming fundamentals
Stored, live, and interactive streaming protocols
Streaming XR content (videos, point clouds, meshes, holograms, spaces)
Local streaming via WiFi, mmWave and optical wireless links
Remote and hybrid rendering
Visual and wireless sensing for person tracking
Networked XR platforms such as ARKit/Core, Unity, Open3D
Building XR systems such as 3D telepresence (VR), Spatial Web (AR)
Tracking fundamentals: Eyes, Hands, Face, Head, Body, etc; Outside-in, Inside-out.

EECE 5698: Networked XR Systems, Spring 2024, Northeastern University

CSE 570: Wireless and Mobile Networks, Spring 2020, Stony Brook University

This class is about fundamental principles of wireless and mobile networking. Some of the topics that we will cover are the following:

Wireless Signals, Properties, Protocols
Wireless Physical Layer
Spectrum Sharing
RF-based Localization
Wireless Link Layer
Mobile IP
Wireless Transport
Mobile and Wireles Applications
Mobile Web
Mobile Video
RF Sensing
Mobile Devices, Performance and Energy Management
Deep Learning in Mobile and Wireless Applications

Academic Service

2025

ACM Transactions on Sensor Networks - Special Issue on Immersive Computing, Guest Editor
USENIX NSDI, Program Committee
IEEE VR, Program Committee
ACM MMSys, Program Committee