Charles Herrmann

papers

1,684

total citations

papers (21)

Kubric: A Scalable Dataset Generator

CVPR 2022arXiv

371

citations

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

NEURIPS 2023arXiv

293

citations

AutoFlow: Learning a Better Training Set for Optical Flow

CVPR 2021arXiv

128

citations

WonderWorld: Interactive 3D Scene Generation from a Single Image

CVPR 2025arXiv

128

citations

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

NEURIPS 2023arXiv

126

citations

Charles Herrmann

papers (21)

Kubric: A Scalable Dataset Generator

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

AutoFlow: Learning a Better Training Set for Optical Flow

WonderWorld: Interactive 3D Scene Generation from a Single Image

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

WonderJourney: Going from Anywhere to Everywhere

Motion Prompting: Controlling Video Generation with Motion Trajectories

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

Pyramid Adversarial Training Improves ViT Performance

Learning to Autofocus

Disentangling Architecture and Training for Optical Flow

VQ3D: Learning a 3D-Aware Generative Model on ImageNet

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions

Accidental Light Probes

Self-Supervised AutoFlow

Deep Survival Analysis With Longitudinal X-Rays for COVID-19

High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion

Channel selection using Gumbel Softmax

Toward Material-Agnostic System Identification from Videos

OCONet: Image Extrapolation by Object Completion

papers (21)

Kubric: A Scalable Dataset Generator

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

AutoFlow: Learning a Better Training Set for Optical Flow

WonderWorld: Interactive 3D Scene Generation from a Single Image

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

WonderJourney: Going from Anywhere to Everywhere

Motion Prompting: Controlling Video Generation with Motion Trajectories

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

Pyramid Adversarial Training Improves ViT Performance

Learning to Autofocus

Disentangling Architecture and Training for Optical Flow

VQ3D: Learning a 3D-Aware Generative Model on ImageNet

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions

Accidental Light Probes

Self-Supervised AutoFlow

Deep Survival Analysis With Longitudinal X-Rays for COVID-19

High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion

Channel selection using Gumbel Softmax

Toward Material-Agnostic System Identification from Videos

OCONet: Image Extrapolation by Object Completion