AIConfPaper
← Search

Steve Seitz

4 accepted papers

2025

Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation

Xiaojuan Wang, Boyang Zhou, Brian Curless, Ira Kemelmacher-Shlizerman, Aleksander Holynski, Steve Seitz
ICLR 2025poster

We present a method for generating video sequences with coherent motion between a pair of input keyframes. We adapt a pretrained large-scale image-to-video diffusion model (originally trained to generate videos moving forward in time from a single input image) for keyframe interpolation, i.e., to pr…

Cited by 7Source ↗PDF ↗Scholar ↗
2025

Linearly Constrained Diffusion Implicit Models

Vivek Jayaram, Ira Kemelmacher-Shlizerman, Steve Seitz, John Thickstun
NeurIPS 2025poster

We introduce Linearly Constrained Diffusion Implicit Models (CDIM), a fast and accurate approach to solving noisy linear inverse problems using diffusion models. Traditional diffusion-based inverse methods rely on numerous projection steps to enforce measurement consistency in addition to unconditio…

Cited by 0Source ↗Scholar ↗
2020

The Cone of Silence: Speech Separation by Localization

Teerapat Jenrungrot, Vivek Jayaram, Steve Seitz, Ira Kemelmacher-Shlizerman
NeurIPS 2020oral

Given a multi-microphone recording of an unknown number of speakers talking concurrently, we simultaneously localize the sources and separate the individual speakers. At the core of our method is a deep network, in the waveform domain, which isolates sources within an angular region $\theta \pm w/2$…

Cited by 65Source ↗PDF ↗code ↗Scholar ↗