Chris Rockwell

I am a Ph.D. candidate in Computer Science and Engineering at the University of Michigan. I do research in computer vision and machine learning and am advised by David F. Fouhey and Justin Johnson. I have been fortunate to collaborate with others, including: Honglak Lee at UM, Jia-Bin Huang at Meta Reality Labs, and Jia Deng at Princeton.

I am actively pursuing computer vision research internships for 2024! Please feel free to reach out: cnris at umich dot edu

Github  /  Google Scholar  /  CV  /  LinkedIn  /  Twitter

profile photo
net1 Scalable 3D Captioning with Pretrained Models
Tiange Luo*, Chris Rockwell*, Honglak Lee and Justin Johnson
NeurIPS (Datasets and Benchmarks Track) 2023
project page / arXiv / Github / bibtex / Hugging Face

Pretrained models are highly effective at 3D captioning; we use them to collect large-scale 3D-text data and finetune text-to-3D models.

net1 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 / Github / bibtex

Small modifications to a ViT enable computations similar to the Eight-Point algorithm, and are a good inductive bias for pose estimation.

net1 PlaneFormers: From Sparse View Planes to 3D Reconstruction
Samir Agarwala, Linyi Jin, Chris Rockwell and David F. Fouhey
ECCV 2022
project page / arXiv / Github / bibtex

Transformers are really good at integrating evidence across multiple views and producing a planar reconstruction.

net1 FWD: Real-time Novel View Synthesis with Forward Warping and Depth
Ang Cao, Chris Rockwell and Justin Johnson
CVPR 2022
project page / arXiv / Github / bibtex / video

Our forward-warping-based method enables real-time, high-quality novel view synthesis on novel objects from sparse views.

net1 Understanding 3D Object Articulation in Internet Videos
Shengyi Qian, Linyi Jin, Chris Rockwell, Siyi Chen and David F. Fouhey
CVPR 2022
project page / arXiv / Github / bibtex / video

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.

net1 PixelSynth: Generating a 3D-Consistent Experience from a Single Image
Chris Rockwell, David F. Fouhey and Justin Johnson
ICCV 2021
project page / PDF / Github / bibtex / press

Combining 3D reasoning and autoregressive modeling facilitates high-quality and consistent single-image novel view synthesis.

net1 Full-Body Awareness from Partial Observations
Chris Rockwell and David F. Fouhey
ECCV 2020
project page / PDF / Github / bibtex / press

A simple self-training framework significantly improves 3D human pose estimation on highly-truncated Internet videos.

meta 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 rival the SOTA meta-learning based method, using higher regularization on fine-tuning layer compared to the backbone.

net1 Hourglass Networks with Top-Down Modulation for Human Pose Estimation
Graduate Research, Princeton Vision and Learning Lab. Summer 2018 - Winter 2019.
Advisor: Jia Deng
Github: Hourglass Implementation / Github: Hourglass Extension

I implement in PyTorch Newell et al.'s Stacked Hourglass Networks, and improve performance using a decoder network as attention.

Professional Experience
meta Meta Reality Labs, Summer - Fall 2022.
Research Scientist Intern (Computational Photography)
Hosts: Hung-Yu Tseng, Jia-Bin Huang, and Johannes Kopf
turingsense TuringSense, Inc., Winter - Spring 2021.
Technical Consultant (Computer Vision).
um2 AI4ALL, Summer 2020, Summer 2021.
Project Instructor (2020) / Project Github
Application Reviewer; Curriculum Advisory Board (2021)
Michigan AI4ALL Lead: David F. Fouhey
um2 African Undergraduate Research Adventure (AURA), Summer 2020.
Graduate Research Mentor
Research Advisor: David F. Fouhey