Search Results for author:
Found 25 papers, 10 papers with code
Reference-Based 3D-Aware Image Editing with Triplane
Generative Adversarial Networks (GANs) have emerged as powerful tools not only for high-quality image generation but also for real image editing through manipulation of their interpretable latent spaces.
Warping the Residuals for Image Editing with StyleGAN
However, their results either suffer from low fidelity to the input image or poor editing qualities, especially for edits that require large transformations.
Diverse Semantic Image Editing with Style Codes
Semantic image editing requires inpainting pixels following a semantic map.
Diverse Inpainting and Editing with GAN Inversion
Specifically, we propose to learn an encoder and mixing network to combine encoded features from erased images with StyleGAN's mapped features from random samples.
Progressive Learning of 3D Reconstruction Network from 2D GAN Data
In this work, to overcome these limitations of generated datasets, we have two main contributions which lead us to achieve state-of-the-art results on challenging objects: 1) A robust multi-stage learning scheme that gradually relies more on the models own predictions when calculating losses, 2) A novel adversarial learning pipeline with online pseudo-ground truth generations to achieve fine details.
Inst-Inpaint: Instructing to Remove Objects with Diffusion Models
From the application point of view, a user needs to generate the masks for the objects they would like to remove which can be time-consuming and prone to errors.
Refining 3D Human Texture Estimation from a Single Image
Estimating 3D human texture from a single image is essential in graphics and vision.
StyleRes: Transforming the Residuals for Real Image Editing with StyleGAN
We present a novel image inversion framework and a training pipeline to achieve high-fidelity image inversion with high-quality attribute editing.
VecGAN: Image-to-Image Translation with Interpretable Latent Directions
However, while those models cannot be trained end-to-end and struggle to edit encoded images precisely, VecGAN is end-to-end trained for image translation task and successful at editing an attribute while preserving the others.
Fine Detailed Texture Learning for 3D Meshes with Generative Models
The reconstruction is posed as an adaptation problem and is done progressively where in the first stage, we focus on learning accurate geometry, whereas in the second stage, we focus on learning the texture with a generative adversarial network.
Benchmarking the Robustness of Instance Segmentation Models
These presented robustness and generalization evaluations are important when designing instance segmentation models for real-world applications and picking an off-the-shelf pretrained model to directly use for the task at hand.
View Generalization for Single Image Textured 3D Models
We describe a cycle consistency loss that encourages model textures to be aligned, so as to encourage sharing.
Dual Contrastive Loss and Attention for GANs
Lastly, we study different attention architectures in the discriminator, and propose a reference attention mechanism.
Neural FFTs for Universal Texture Image Synthesis
The conventional CNNs, recently adopted for synthesis, require to train and test on the same set of images and fail to generalize to unseen images.
Panoptic-based Image Synthesis
Conditional image synthesis for generating photorealistic images serves various applications for content editing to content generation.
Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos
However, the reconstruction task of the entire image forces the model to allocate landmarks to model the background.
Video Interpolation and Prediction with Unsupervised Landmarks
Prediction and interpolation for long-range video data involves the complex task of modeling motion trajectories for each visible object, occlusions and dis-occlusions, as well as appearance changes due to viewpoint and lighting.
Unsupervised Video Interpolation Using Cycle Consistency
We further introduce a pseudo supervised loss term that enforces the interpolated frames to be consistent with predictions of a pre-trained interpolation model.
Ranked #1 on
Video Frame Interpolation
on UCF101
(PSNR (sRGB) metric)
Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
Deep neural networks have largely failed to effectively utilize synthetic data when applied to real images due to the covariate shift problem.
Context Augmentation for Convolutional Neural Networks
Recent enhancements of deep convolutional neural networks (ConvNets) empowered by enormous amounts of labeled data have closed the gap with human performance for many object recognition tasks.
Human-like Clustering with Deep Convolutional Neural Networks
We do not dwell much on the learning mechanisms in these frameworks as they are still a matter of debate, with respect to biological constraints.
Robust Convolutional Neural Networks under Adversarial Noise
Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called "adversarial examples".
Convolutional Clustering for Unsupervised Learning
In this work, we propose to train a deep convolutional network based on an enhanced version of the k-means clustering algorithm, which reduces the number of correlated parameters in the form of similar filters, and thus increases test categorization accuracy.
Ranked #69 on
Image Classification
on MNIST
Flattened Convolutional Neural Networks for Feedforward Acceleration
We present flattened convolutional neural networks that are designed for fast feedforward execution.
An Analysis of the Connections Between Layers of Deep Neural Networks
On the other hand, in unsupervised learning, one cannot rely on back-propagation techniques to learn the connections between layers.
