Visual computing tasks such as computational imaging, image/video understanding, generative AI, and real-time 3D graphics are key responsibilities of modern computer systems ranging from sensor-rich smart phones, autonomous robots, and large datacenters. These workloads demand exceptional system efficiency and this course examines the key ideas, techniques, and challenges associated with the design of parallel, heterogeneous systems that accelerate visual computing applications. This course is intended for systems students interested in architecting efficient graphics, image processing, and computer vision platforms (both new hardware architectures and domain-optimized programming frameworks for these platforms) and for graphics, vision, and AI students that wish to understand throughput computing principles to design new algorithms that map efficiently to these machines.
Apr 02 |
|
Discussion of modern visual computing applications, a design exercise
|
Apr 04 |
|
Algorithms for taking raw sensor pixels to an RGB image: demosaicing, sharpening, correcting lens aberrations, multi-shot alignment/merging, image filtering, multi-scale processing with Gaussian and Laplacian pyramids, HDR (local tone mapping)
|
Apr 09 |
|
The Frankencamera, modern camera APIs, advanced image analysis for photography (portrait mode, autofocus, etc)
|
Apr 11 |
|
Balancing locality, parallelism, and work, fusion and tiling, design of the Halide domain-specific language, automatically scheduling image processing pipelines
|
Apr 16 |
|
Detailed look at Halide's scheduling algebra
|
Apr 18 |
|
Data-layout optimizations, scheduling decisions, fusion optimizations, modern libraries (like CUTLASS)
|
Apr 23 |
|
GPUs, TPUs, special instructions for DNN evaluation (and their efficiency vs custom ASIC), choice of precision in arithmetic, modern commercial DNN accelerators, flexibility vs efficiency trade-offs
|
Apr 25 |
|
The importance of predictable control in content creation. Techniques for inserting new forms of control into generative image synthesis, role of human-interpretable abstractions.
|
Apr 30 |
|
Generative Image Synthesis - Part II (Efficient Generation)
Modern techniques for generating images efficiently with generative AI: stable diffusion, low-dimensional spaces, consistency matching, how it comes together in SDXL Turbo
|
May 02 |
|
Generating new types of media (video, animation, 3D, worlds and more)
Video generation (like Sora), generating 3D content, virtual worlds, generating programs
|
May 07 |
|
Creating AI Agents (Including LLM-based problem solving)
LLM-based problem solving agents, systems and platforms for developing AI agents
|
May 09 |
|
Fast 3D World Simulation for Model Training (Part I)
Training agents in virtual worlds, simulation engines for training agents, throughput-maximized engines, sim-to-real issues, hybrid RL-LLM systems
|
May 14 |
|
Fast 3D World Simulation for Model Training (Part II)
Discussion of high-throughput systems like Madrona, and pixel based systems like DeepMind's Genie
|
May 16 |
|
Differentiable Rendering and Optimizable Representations for 3D Reconstruction (Part I)
Scene representations such as NeRF, dense volumes, sparse-octrees, neural Hash-Grids, 3D gaussians
|
May 21 |
|
Differentiable Rendering and Optimizable Representations for 3D Reconstruction (Part II)
Gaussian splatting and its performance optimization. Ray casting vs. rasterization.
|
May 23 |
|
Video Compression: Traditional and Learned
H.264 video representation/encoding, parallel encoding, motivations for ASIC acceleration, ML-based compression methods, emerging opportunities for compression when machines, not humans, will observe most images
|
May 28 |
|
The Present and Future of Videoconferencing Systems
System design issues for building a video conferencing system: reducing latency, bandwidth, etc. How real-time video analysis will enable richer video-based applications.
|
Jun 5 | Term Project Information |