Chris Rockwell

I am a final year Ph.D. student in Computer Science and Engineering at the University of Michigan and a visiting student at New York University. 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 Deng at Princeton, Jia-Bin Huang at Meta Reality Labs and Chen-Hsuan Lin at NVIDIA Deep Imagination Research.

I am actively pursuing research scientist positions for 2025! Please feel free to contact me: cnris at umich dot edu

GitHub  /  Google Scholar  /  CV  /  LinkedIn  /  Twitter

We introduce DynPose-100K, a large-scale video dataset of dynamic content with camera annotations.

Our flexible method produces accurate and robust pose estimates using complementary strengths of Correspondence + Solver and Learning-Based methods.

Pretrained models are highly effective at 3D captioning; we use them to collect large-scale 3D-text dataset Cap3D 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 very effective 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.

Template