Search Results for author:
Found 15 papers, 7 papers with code
Explorative Inbetweening of Time and Space
We introduce bounded generation as a generalized task to control video generation to synthesize arbitrary camera and subject motion based only on a given start and end frame.
Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos
We show that by using simple segmentations and coarse 2D manipulations, we can synthesize a photorealistic edit faithful to the user's input while addressing second-order effects like harmonizing the lighting and physical interactions between edited objects.
Restoration by Generation with Constrained Priors
We propose a method to adapt a pretrained diffusion model for image restoration by simply adding noise to the input image to be restored and then denoise.
DiffusionRig: Learning Personalized Priors for Facial Appearance Editing
On a high level, DiffusionRig learns to map simplistic renderings of 3D face models to realistic photos of a given person.
Semi-supervised Parametric Real-world Image Harmonization
Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo.
Self-Supervised Burst Super-Resolution
Extensive experiments on real and synthetic data show that, despite only using noisy bursts during training, models trained with our self-supervised strategy match, and sometimes surpass, the quality of fully-supervised baselines trained with synthetic data or weakly-paired ground-truth.
The Implicit Values of A Good Hand Shake: Handheld Multi-Frame Neural Depth Refinement
Modern smartphones can continuously stream multi-megapixel RGB images at 60Hz, synchronized with high-quality 3D pose information and low-resolution LiDAR-driven depth estimates.
A Dark Flash Normal Camera
Casual photography is often performed in uncontrolled lighting that can result in low quality images and degrade the performance of downstream processing.
Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments
We introduce a neural network-based method to denoise pairs of images taken in quick succession, with and without a flash, in low-light environments.
Basis Prediction Networks for Effective Burst Denoising with Large Kernels
Bursts of images exhibit significant self-similarity across both time and space.
Training Image Estimators without Image Ground Truth
Deep neural networks have been very successful in compressive-sensing and image restoration applications, as a means to estimate images from partial, blurry, or otherwise degraded measurements.
Generating and Exploiting Probabilistic Monocular Depth Estimates
Beyond depth estimation from a single image, the monocular cue is useful in a broader range of depth inference applications and settings---such as when one can leverage other available depth cues for improved accuracy.
Ranked #65 on
Monocular Depth Estimation
on NYU-Depth V2
(RMSE metric)
Training Image Estimators without Image Ground-Truth
We evaluate our method for training networks for compressive-sensing and blind deconvolution, considering both non-blind and blind training for the latter.
Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising
In this work, we propose a new method for natural image denoising that trains a deep neural network to determine whether patches in a noisy image input share common underlying patterns.
Efficient and accurate inversion of multiple scattering with deep learning
Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography.
