inline-defaultCreated with Sketch.
inline-defaultCreated with Sketch.
HomeUniversitiesProgramsStudents & Alumni
search
Students
Masters

Visual Computing Systems

Stanford University
California , United States
Visit Program Website
Students
Tuition Fee
Not Available
Start Date
Not Available
Medium of studying
Not Available
Duration
Not Available
Details
About Program
About University
Gallery
Contact School
Details
Program Details
Degree
Masters
Major
Artificial Intelligence | Computer Science | Software Engineering
Area of study
Information and Communication Technologies | Engineering
Course Language
English
About Program

Program Overview

Program Overview

The Stanford CS348V program, offered in Winter 2018, focuses on Visual Computing Systems. This course examines the key ideas, techniques, and challenges associated with the design of parallel, heterogeneous systems that accelerate visual computing applications.


Course Description

Visual computing tasks, such as computational imaging, image/video understanding, and real-time 3D graphics, are key responsibilities of modern computer systems. These workloads demand exceptional system efficiency, and this course is intended for systems students interested in architecting efficient graphics, image processing, and computer vision platforms.


Basic Information

  • The course is held on Tuesdays and Thursdays from 1:30-2:50pm in Mitchell Earth Sciences B67.
  • The instructor is Kayvon Fatahalian.

Course Schedule

The Winter 2018 schedule is as follows:


  • Jan 9: Course Introduction + Review of Parallel Hardware Architecture
  • Jan 11: Overview of a Modern Digital Camera Processing Pipeline
  • Jan 16: Camera Pipeline Part II + Image Processing Algorithms
  • Jan 18: Efficiently Scheduling Image Processing Algorithms on Parallel Hardware
  • Jan 23: Specialized Hardware for Image Processing
  • Jan 25: Lossy Image (JPG) and Video (H.264) Compression
  • Jan 30: The Light Field, Computational Cameras, and Display/Capture for VR
  • Feb 1: Workload Characteristics of DNN Inference for Image Analysis
  • Feb 6: Scheduling and Algorithms for Parallel DNN Training at Scale
  • Feb 8: A Case Study of Algorithmic Optimizations for Object Detection
  • Feb 13: Leveraging Task-Specific DNN Structure for Improving Performance and Accuracy
  • Feb 15: Hardware Accelerators for DNN Inference
  • Feb 20: Optimizing Inference on Video Streams
  • Feb 22: Video Processing at Datacenter Scale
  • Feb 27: Real-Time 3D Graphics Pipeline Architecture
  • Mar 1: Hardware Acceleration of Texture Mapping and Depth-Buffering
  • Mar 6: Scheduling the Graphics Pipeline onto a GPU
  • Mar 8: Large Scale Distributed Image Processing at Facebook (guest lecture)
  • Mar 13: Domain Specific Languages for Shading
  • Mar 15: Topic TBD

Assignments and Projects

  • All students are expected to perform academic paper readings approximately every other class.
  • Students must complete three simple programming exercises to reinforce concepts.
  • A self-selected final project is required, which can be performed in teams of up to two.
  • Assignment due dates:
    • Jan 19: Assignment 1: Performance Analysis on a Multi-Core CPU
    • Feb 7: Assignment 2: RAW Processing for the kPhone 348V
    • Mar 16: Assignment 3: Scheduling a MobileNet Layer (optional)
    • End of quarter: Self-Selected Term Project

Copyright

Copyright 2018 Stanford University.


See More