Chris Rockwell

I am an AI Scientist working on large-scale generative models for Roblox Reality, with the goal of enabling photorealistic gaming. Previously, I was part of the founding team at Morpheus AI under Xun Huang, which was acquired by Roblox.

I received a Ph.D. in Computer Science from the University of Michigan, advised by Justin Johnson and David F. Fouhey. I also interned at NVIDIA Deep Imagination Research with Chen-Hsuan Lin and Tsung-Yi Lin, and at Meta Reality Labs with Hung-Yu Tseng and Jia-Bin Huang.

Across these roles, I have built data pipelines at scale and designed and trained models, from camera pose estimation and 3D generation to real-time video generation and world models.

GitHub  /  Google Scholar  /  CV  /  LinkedIn  /  X

We lift a pretrained latent video model into pixel space, enabling efficient high-resolution video, precise video editing and low-latency world modeling.

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.

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

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

Template