Diagnostic Evaluation of Video Inpainting on Landscapes (DEVIL)
A benchmark for evaluating video inpainting models in a fine-grained, replicable manner.
HyperCon: Image-To-Video Model Transfer for Video-To-Video Translation Tasks
Enabling temporally-consistent style transfer and inpainting via interpolation and aggregation.
A Temporally-Aware Interpolation Network for Video Frame Inpainting
Filling in missing frames by blending bidirectional predictions with a temporally-aware interpolation network.
A Dataset To Evaluate The Representations Learned By Video Prediction Models (Moving Symbols)
The Moving Symbols dataset designed to expose generalization issues with existing video prediction networks.
Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation
Improving viewpoint estimation by integrating information about a single keypoint.
Presentations Automatically Organized from Lectures (PAOL)
Automated lecture capture system that I worked on at UMass Amherst.
Feature-Based CAD Data Exchange
The project that I worked on with the UMass Center for e-Design during my REU in summer 2012.