6 papers
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
Ahan Shabanov, Peter Hedman, Ethan Weber +10
We present Free-Range Gaussians, a multi-view reconstruction method that predicts non-pixel, non-voxel-aligned 3D Gaussians from as few as four images. This is done through flow ma…
Fillerbuster: Unified Generative Scene Completion Model for Casual Captures
Ethan Weber, Norman Müller, Yash Kant +4
We present Fillerbuster, a unified model that completes unknown regions of a 3D scene with a multi-view latent diffusion transformer. Casual captures are often sparse and miss surr…
Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop
Justin Kerr, Kush Hari, Ethan Weber +5
Humans do not passively observe the visual world -- we actively look in order to act. Motivated by this principle, we introduce EyeRobot, a robotic system with gaze behavior that e…
Flow Matching Policy Gradients
David McAllister, Songwei Ge, Brent Yi +5
Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization…
Pippo: High-Resolution Multi-View Humans from a Single Image
Yash Kant, Ethan Weber, Jin Kyu Kim +6
We present Pippo, a generative model capable of producing 1K resolution dense turnaround videos of a person from a single casually clicked photo. Pippo is a multi-view diffusion tr…
Toon3D: Seeing Cartoons from New Perspectives
Ethan Weber, Riley Peterlinz, Rohan Mathur +3
We recover the underlying 3D structure from images of cartoons and anime depicting the same scene. This is an interesting problem domain because images in creative media are often…