Jeff Tan

Hello! I'm a first-year MS in Robotics student at Carnegie Mellon University, advised by Prof. Deva Ramanan. My research interests are in computer vision and graphics, for example perceiving and interacting with dynamic 3D scenes. Previously, I did my undergrad in CS at CMU.

Resume  /  Email  /  Github

profile photo
Research

Distilling Neural Fields for Real-Time Articulated Shape Reconstruction
Jeff Tan, Gengshan Yang, Deva Ramanan
CVPR 2023
project page | paper

A method to learn real-time feed-forward shape predictors, by distilling knowledge from offline differentiable rendering optimizers.

Projects

Lab4D
Gengshan Yang, Jeff Tan, Alex Lyons, Neehar Peri, Deva Ramanan
Docs Github

A Python library for 4D reconstruction from videos.

Dirt Renderer
Jeff Tan
report

A physics-based renderer for photorealistic images that supports Monte Carlo path tracing with physically realistic materials, as well as bidirectional path tracing, volume rendering, and CPU parallelism.

Hulk Compiler
Jeff Tan, Rachel Yuan
report

A compiler for a type-safe subset of C, supporting many optimizations such as static single assignment, register allocation, constant/copy propagation, dataflow analysis, partial redundancy elimination, dead code elimination, and alias analysis. We outperform gcc -O1 by 36.9% on average on CMU 15-411's benchmark suite.

Misc
CMU SCS Logo Teaching Assistant, Physics-Based Rendering (15-468, S23)
Teaching Assistant, Parallel Computation (15-418, F21, S22, S23)
Teaching Assistant, Introduction to Computer Systems (15-213, F21)

Credits to Jon Barron for this website's template.