|
The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs
Chris Rockwell,
Justin Johnson
and David F. Fouhey
3DV 2022
project page /
PDF /
code /
bibtex
Small modifications to a ViT enable computations
similar to the Eight-Point algorithm,
and are a good inductive bias for pose estimation.
|
|
PlaneFormers: From Sparse View Planes to 3D Reconstruction
Samir Agarwala,
Linyi Jin,
Chris Rockwell and
David F. Fouhey
ECCV 2022
project page /
arXiv /
code /
bibtex
Transformers are really good at integrating evidence across multiple views and producing a planar reconstruction.
|
|
FWD: Real-time Novel View Synthesis with Forward Warping and Depth
Ang Cao,
Chris Rockwell and
Justin Johnson
CVPR 2022
project page /
arXiv /
video /
code
Our forward-warping-based method enables real-time, high-quality novel view synthesis on novel objects from sparse views.
|
|
Understanding 3D Object Articulation in Internet Videos
Shengyi Qian,
Linyi Jin,
Chris Rockwell,
Siyi Chen and
David F. Fouhey
CVPR 2022
project page /
arXiv /
code /
bibtex /
CVPR talk
By training on both video data and 3D reconstructions in the right way, we can build models of articulations of 3D objects on ordinary video data.
|
|
PixelSynth: Generating a 3D-Consistent Experience from a Single Image
Chris Rockwell, David F. Fouhey and Justin Johnson
ICCV 2021
project page /
PDF /
code /
bibtex /
press
Combining 3D reasoning and autoregressive modeling facilitates high-quality and consistent single-image novel view synthesis.
|
|
Full-Body Awareness from Partial Observations
Chris Rockwell and David F. Fouhey
ECCV 2020
project page /
PDF /
code /
bibtex /
press
A simple self-training framework significantly improves 3D human pose estimation on highly-truncated Internet videos.
|
|
Hourglass Networks with Top-Down Modulation for Human Pose Estimation
Graduate Research, Princeton Vision and Learning Lab. Summer 2018 - Winter 2019.
Advisor: Jia Deng
code: attention / pretrained model, 2HG attention
code: regularization / pretrained model, 8HG regularization
We increase performance of Newell et al.'s Stacked Hourglass Networks on MPII using a decoder network as attention, along with
cutout and vertical flipping.
In addition, we improved precision of network confidence and explored utilizing confidence for curriculum sampling of tail cases.
|
|
A Simple Baseline on Meta-Dataset
Graduate Research, Princeton Vision and Learning Lab. Spring 2019.
Advisor: Jia Deng
We improve a simple fine-tuning baseline on Meta-Dataset to within 0.1 average rank (minimum reportable difference) of the authors' best meta-learning based method using higher regularization on fine-tuning layer compared to the backbone.
|
|
Evaluating Scene Graph-Generated Images using Visual Question Answering
Chris Rockwell.
Course project, EECS 692 Advanced AI, Winter 2019.
Instructor: John Laird.
presentation / report
I replicate and summarize
Image Generation from Scene Graphs
, and evaluate replicated generated images, original generated images, and ground truths using VQA.
|
|
Replicating and Improving Stacked Hourglass Networks for Human Pose Estimation
Chris Rockwell, Uzziel Cortez, Eric Huang.
Course project, EECS 545 Machine Learning, Fall 2018.
Instructor: Clayton Scott.
report / code / pretrained model, 8HG
We replicate and improve upon validation accuracy from
Stacked Hourglass Networks for Human Pose Estimation
using Adam and larger batch size. I led implementation of the project and it was jointly useful for research. My Pytorch implementation is published in the princeton-vl Github.
|
|
GTA Perception
Richard Higgins, Parth Chopra, Chris Rockwell, Sahib Dhanjal, Ung Hee Lee.
Course project, EECS 598/ROB 535 Self-Driving Cars, Fall 2018.
Instructors: Matthew Johnson-Roberson and Ram Vasudevan
code
We finetune a Squeeze and Excitation ResNet classify objects appearing in road-scene images in the Driving in the Matrix dataset. With improved sampling and data augmentation, we finished top 10 in the class. I helped with implementation and improved data augmentation.
|
|
Link Prediction on the Patent Citation Network
Samuel Chen, David Dang, Robert Macy, Chris Rockwell.
Course project, EECS 598 Advanced Data Mining, Winter 2019.
Instructor: Danai Koutra.
poster / report / code
We compare several methods for link prediction on partitions of the Patent Citation Network dataset for the first time. The very sparse nature of this graph yielded low performance compared to a more typical dataset, but methods performed well in a temporal setting. I led temporal experiments and adapted representation learning method SDNE for our task.
|
|
Market Fragmentation and the Latency Arms Race
Undergraduate Research, Strategic Reasoning Group. Summer 2013.
Advisor: Michael Wellman
poster / presentation
I was featured in a UMSI Youtube video.
I assisted Erik Brinkman in expanding the agent-based latency arbitrage simulation of Wah and Wellman to model a prisoner's dilemma in the high-frequency trading space.
|
|
AI4ALL, Summer 2020: Project Instructor
Summer 2021: Application Reviewer, Curriculum Advisory Board
Michigan AI4ALL Lead: David F. Fouhey
|
|
African Undergraduate Research Adventure (AURA), Summer 2020: Research Mentor
Research Advisor: David F. Fouhey
|
|
EECS 498/598 Deep Learning, Winter 2019: Grader
Instructor: Honglak Lee
|
 |
Guest blog post on Miles Kimball's Economics blog Confessions of a Supply Side Liberal
post
|
|