Aleksander Holynski

17

Papers

550

Total Citations

Papers (17)

ReconFusion: 3D Reconstruction with Diffusion Priors

Generative Image Dynamics

Video Interpolation with Diffusion Models

Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos

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

Generative Powers of Ten

Dual-Process Image Generation

SimVS: Simulating World Inconsistencies for Robust View Synthesis

GPS as a Control Signal for Image Generation

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos

ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models

NeRFiller: Completing Scenes via Generative 3D Inpainting

Readout Guidance: Learning Control from Diffusion Features

Continuous 3D Perception Model with Persistent State

Bolt3D: Generating 3D Scenes in Seconds

Disentangled 3D Scene Generation with Layout Learning