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

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

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

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

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

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.

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

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

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.

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

Template