Search Results for author: Aleksander Holynski

Found 36 papers, 7 papers with code

How Animals Dance (When You're Not Looking)

no code implementations29 May 2025 Xiaojuan Wang, Aleksander Holynski, Brian Curless, Ira Kemelmacher, Steve Seitz

We present a keyframe-based framework for generating music-synchronized, choreography aware animal dance videos.

Image Generation

GPS as a Control Signal for Image Generation

no code implementations CVPR 2025 Chao Feng, Ziyang Chen, Aleksander Holynski, Alexei A. Efros, Andrew Owens

We show that the GPS tags contained in photo metadata provide a useful control signal for image generation.

Image Generation

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

no code implementations CVPR 2025 Zhengqi Li, Richard Tucker, Forrester Cole, Qianqian Wang, Linyi Jin, Vickie Ye, Angjoo Kanazawa, Aleksander Holynski, Noah Snavely

We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes.

Depth Estimation

SimVS: Simulating World Inconsistencies for Robust View Synthesis

no code implementations CVPR 2025 Alex Trevithick, Roni Paiss, Philipp Henzler, Dor Verbin, Rundi Wu, Hadi AlZayer, Ruiqi Gao, Ben Poole, Jonathan T. Barron, Aleksander Holynski, Ravi Ramamoorthi, Pratul P. Srinivasan

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are difficult to model explicitly.

Novel View Synthesis

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

1 code implementation5 Dec 2024 Zhengqi Li, Richard Tucker, Forrester Cole, Qianqian Wang, Linyi Jin, Vickie Ye, Angjoo Kanazawa, Aleksander Holynski, Noah Snavely

We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes.

Depth Estimation

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

no code implementations27 Aug 2024 Xiaojuan Wang, Boyang Zhou, Brian Curless, Ira Kemelmacher-Shlizerman, Aleksander Holynski, Steven M. Seitz

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 key frame interpolation, i. e., to produce a video in between two input frames.

Diffusion Models as Data Mining Tools

no code implementations20 Jul 2024 Ioannis Siglidis, Aleksander Holynski, Alexei A. Efros, Mathieu Aubry, Shiry Ginosar

Concretely, we show that after finetuning conditional diffusion models to synthesize images from a specific dataset, we can use these models to define a typicality measure on that dataset.

Image Generation

Rethinking Score Distillation as a Bridge Between Image Distributions

no code implementations13 Jun 2024 David McAllister, Songwei Ge, Jia-Bin Huang, David W. Jacobs, Alexei A. Efros, Aleksander Holynski, Angjoo Kanazawa

We compare our method to existing approaches for score distillation sampling and show that it can produce high-frequency details with realistic colors.

NeRF

CAT3D: Create Anything in 3D with Multi-View Diffusion Models

no code implementations16 May 2024 Ruiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee, Ricardo Martin-Brualla, Pratul Srinivasan, Jonathan T. Barron, Ben Poole

Advances in 3D reconstruction have enabled high-quality 3D capture, but require a user to collect hundreds to thousands of images to create a 3D scene.

3D Reconstruction

Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis

no code implementations13 May 2024 Yifan Wang, Aleksander Holynski, Brian L. Curless, Steven M. Seitz

We present Infinite Texture, a method for generating arbitrarily large texture images from a text prompt.

Texture Synthesis

Readout Guidance: Learning Control from Diffusion Features

no code implementations CVPR 2024 Grace Luo, Trevor Darrell, Oliver Wang, Dan B Goldman, Aleksander Holynski

We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals.

Generative Powers of Ten

no code implementations CVPR 2024 Xiaojuan Wang, Janne Kontkanen, Brian Curless, Steve Seitz, Ira Kemelmacher, Ben Mildenhall, Pratul Srinivasan, Dor Verbin, Aleksander Holynski

We present a method that uses a text-to-image model to generate consistent content across multiple image scales, enabling extreme semantic zooms into a scene, e. g., ranging from a wide-angle landscape view of a forest to a macro shot of an insect sitting on one of the tree branches.

Image Super-Resolution

State of the Art on Diffusion Models for Visual Computing

no code implementations11 Oct 2023 Ryan Po, Wang Yifan, Vladislav Golyanik, Kfir Aberman, Jonathan T. Barron, Amit H. Bermano, Eric Ryan Chan, Tali Dekel, Aleksander Holynski, Angjoo Kanazawa, C. Karen Liu, Lingjie Liu, Ben Mildenhall, Matthias Nießner, Björn Ommer, Christian Theobalt, Peter Wonka, Gordon Wetzstein

The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes.

RealFill: Reference-Driven Generation for Authentic Image Completion

no code implementations28 Sep 2023 Luming Tang, Nataniel Ruiz, Qinghao Chu, Yuanzhen Li, Aleksander Holynski, David E. Jacobs, Bharath Hariharan, Yael Pritch, Neal Wadhwa, Kfir Aberman, Michael Rubinstein

Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene.

Generative Image Dynamics

1 code implementation CVPR 2024 Zhengqi Li, Richard Tucker, Noah Snavely, Aleksander Holynski

We present an approach to modeling an image-space prior on scene motion.

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

no code implementations NeurIPS 2023 Grace Luo, Lisa Dunlap, Dong Huk Park, Aleksander Holynski, Trevor Darrell

We propose Diffusion Hyperfeatures, a framework for consolidating multi-scale and multi-timestep feature maps into per-pixel feature descriptors that can be used for downstream tasks.

Semantic correspondence

Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs

1 code implementation ICCV 2023 Frederik Warburg, Ethan Weber, Matthew Tancik, Aleksander Holynski, Angjoo Kanazawa

Casually captured Neural Radiance Fields (NeRFs) suffer from artifacts such as floaters or flawed geometry when rendered outside the camera trajectory.

NeRF Novel View Synthesis

InstructPix2Pix: Learning to Follow Image Editing Instructions

6 code implementations CVPR 2023 Tim Brooks, Aleksander Holynski, Alexei A. Efros

We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image.

Image Editing +4

SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage

no code implementations CVPR 2023 Yifan Wang, Aleksander Holynski, Xiuming Zhang, Xuaner Zhang

Our method only requires the user to capture a selfie video outdoors, rotating in place, and uses the varying angles between the sun and the face as guidance in joint reconstruction of facial geometry, reflectance, camera pose, and lighting parameters.

Novel View Synthesis

Animating Pictures with Eulerian Motion Fields

no code implementations CVPR 2021 Aleksander Holynski, Brian Curless, Steven M. Seitz, Richard Szeliski

In this paper, we demonstrate a fully automatic method for converting a still image into a realistic animated looping video.

Image-to-Image Translation Translation

Reducing Drift in Structure From Motion Using Extended Features

no code implementations27 Aug 2020 Aleksander Holynski, David Geraghty, Jan-Michael Frahm, Chris Sweeney, Richard Szeliski

Low-frequency long-range errors (drift) are an endemic problem in 3D structure from motion, and can often hamper reasonable reconstructions of the scene.

Seeing the World in a Bag of Chips

no code implementations CVPR 2020 Jeong Joon Park, Aleksander Holynski, Steve Seitz

We address the dual problems of novel view synthesis and environment reconstruction from hand-held RGBD sensors.

Novel View Synthesis

Structure from Motion for Panorama-Style Videos

no code implementations8 Jun 2019 Chris Sweeney, Aleksander Holynski, Brian Curless, Steve M Seitz

We present a novel Structure from Motion pipeline that is capable of reconstructing accurate camera poses for panorama-style video capture without prior camera intrinsic calibration.

Cannot find the paper you are looking for? You can Submit a new open access paper.