Search Results for author:
Found 21 papers, 11 papers with code
Robust High-Resolution Video Matting with Temporal Guidance
We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance.
Real-Time High-Resolution Background Matting
We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU.
Background Matting: The World is Your Green Screen
To bridge the domain gap to real imagery with no labeling, we train another matting network guided by the first network and by a discriminator that judges the quality of composites.
Ranked #1 on
Image Matting
on Adobe Matting
Lifespan Age Transformation Synthesis
Most existing aging methods are limited to changing the texture, overlooking transformations in head shape that occur during the human aging and growth process.
Universal Guidance for Diffusion Models
Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining.
rPPG-Toolbox: Deep Remote PPG Toolbox
Camera-based physiological measurement is a fast growing field of computer vision.
SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild
SfSNet learns from a mixture of labeled synthetic and unlabeled real world images.
Towards Unified Keyframe Propagation Models
We evaluate our two-stream approach for inpainting tasks, where experiments show that it improves both the propagation of features within a single frame as required for image inpainting, as well as their propagation from keyframes to target frames.
Shape and Material Capture at Home
In this paper, we present a technique for estimating the geometry and reflectance of objects using only a camera, flashlight, and optionally a tripod.
Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement
Our findings illustrate the usefulness of motion transfer as a data augmentation technique for improving the generalization of models for camera-based physiological sensing.
MVPSNet: Fast Generalizable Multi-view Photometric Stereo
We propose a fast and generalizable solution to Multi-view Photometric Stereo (MVPS), called MVPSNet.
A New Rank Constraint on Multi-view Fundamental Matrices, and its Application to Camera Location Recovery
We show that in general, with the selection of proper scale factors, a matrix formed by stacking fundamental matrices between pairs of images has rank 6.
Solving Uncalibrated Photometric Stereo Using Fewer Images by Jointly Optimizing Low-rank Matrix Completion and Integrability
We introduce a new, integrated approach to uncalibrated photometric stereo.
SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild'
SfSNet learns from a mixture of labeled synthetic and unlabeled real world images.
Neural Inverse Rendering of an Indoor Scene from a Single Image
Inverse rendering aims to estimate physical attributes of a scene, e. g., reflectance, geometry, and lighting, from image(s).
A Light Stage on Every Desk
Whereas existing light stages require expensive, room-scale spherical capture gantries and exist in only a few labs in the world, we demonstrate how to acquire useful data from a normal TV or desktop monitor.
Fast Light-Weight Near-Field Photometric Stereo
Existing approaches rely on optimization coupled with a far-field PS network operating on pixels or small patches.
A Surface-normal Based Neural Framework for Colonoscopy Reconstruction
Reconstructing a 3D surface from colonoscopy video is challenging due to illumination and reflectivity variation in the video frame that can cause defective shape predictions.
Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation
We then finetune different algorithms on our MAW dataset to significantly improve the quality of the reconstructed albedo both quantitatively and qualitatively.
$\texttt{NePhi}$: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registration
In contrast to the predominant voxel-based transformation fields used in learning-based registration approaches, NePhi represents deformations functionally, leading to great flexibility within the design space of memory consumption during training and inference, inference time, registration accuracy, as well as transformation regularity.
