Search Results for author:
Found 67 papers, 38 papers with code
DeepLandscape: Adversarial Modeling of Landscape Videos
Furthermore, by fitting the learned models to a static landscape image, the latter can be reenacted in a realistic way.
MoRF: Mobile Realistic Fullbody Avatars from a Monocular Video
We present a new approach for learning Mobile Realistic Fullbody (MoRF) avatars.
DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars
We present DINAR, an approach for creating realistic rigged fullbody avatars from single RGB images.
Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions
Namely, we extend NeuS, a state-of-the-art neural implicit function formulation, to represent multiple objects of a class (human heads in our case) simultaneously.
MegaPortraits: One-shot Megapixel Neural Head Avatars
In this work, we advance the neural head avatar technology to the megapixel resolution while focusing on the particularly challenging task of cross-driving synthesis, i. e., when the appearance of the driving image is substantially different from the animated source image.
Realistic One-shot Mesh-based Head Avatars
We present a system for realistic one-shot mesh-based human head avatars creation, ROME for short.
NPBG++: Accelerating Neural Point-Based Graphics
We present a new system (NPBG++) for the novel view synthesis (NVS) task that achieves high rendering realism with low scene fitting time.
Stereo Magnification with Multi-Layer Images
The second stage infers the color and the transparency values for these layers producing the final representation for novel view synthesis.
Ranked #1 on
Novel View Synthesis
on SWORD
Resolution-robust Large Mask Inpainting with Fourier Convolutions
We find that one of the main reasons for that is the lack of an effective receptive field in both the inpainting network and the loss function.
Ranked #3 on
Seeing Beyond the Visible
on KITTI360-EX
Perceptual Gradient Networks
The use of perceptual loss however incurs repeated forward-backward passes in a large image classification network as well as a considerable memory overhead required to store the activations of this network.
StylePeople: A Generative Model of Fullbody Human Avatars
We show that with the help of neural textures, such avatars can successfully model clothing and hair, which usually poses a problem for mesh-based approaches.
Point-Based Modeling of Human Clothing
We propose a new approach to human clothing modeling based on point clouds.
Real-time RGBD-based Extended Body Pose Estimation
We use parametric 3D deformable human mesh model (SMPL-X) as a representation and focus on the real-time estimation of parameters for the body pose, hands pose and facial expression from Kinect Azure RGB-D camera.
CNN with large memory layers
We have tested the memory layer on the classification, image reconstruction and relocalization problems and found that for some of those, the memory layers can provide significant speed/accuracy improvement with the high utilization of the key-value elements, while others require more careful fine-tuning and suffer from dying keys.
Relightable 3D Head Portraits from a Smartphone Video
The model is fitted to the sequence of frames with human face-specific priors that enforce the plausibility of albedo-lighting decomposition and operates at the interactive frame rate.
Image Generators with Conditionally-Independent Pixel Synthesis
Existing image generator networks rely heavily on spatial convolutions and, optionally, self-attention blocks in order to gradually synthesize images in a coarse-to-fine manner.
Ranked #1 on
Image Generation
on Satellite-Landscapes 256 x 256
TRANSPR: Transparency Ray-Accumulating Neural 3D Scene Point Renderer
New scenes can be modeled using gradient-based optimization of neural descriptors and of the rendering network.
Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars
The texture image is generated offline, warped and added to the coarse image to ensure a high effective resolution of synthesized head views.
DeepLandscape: Adversarial Modeling of Landscape Video
Furthermore, by fitting the learned models to a static landscape image, the latter can be reenacted in a realistic way.
Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks
We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks.
Ranked #25 on
Semantic Segmentation
on S3DIS
Neural Head Reenactment with Latent Pose Descriptors
We propose a neural head reenactment system, which is driven by a latent pose representation and is capable of predicting the foreground segmentation alongside the RGB image.
High-Resolution Daytime Translation Without Domain Labels
We present the high-resolution daytime translation (HiDT) model for this task.
Stereo relative pose from line and point feature triplets
In this work, we present two minimal solvers for the stereo relative pose.
Neural Point-Based Graphics
A deep rendering network is learned in parallel with the descriptors, so that new views of the scene can be obtained by passing the rasterizations of a point cloud from new viewpoints through this network.
Textured Neural Avatars
In particular, our system estimates an explicit two-dimensional texture map of the model surface.
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
In order to create a personalized talking head model, these works require training on a large dataset of images of a single person.
Learnable Triangulation of Human Pose
We present two novel solutions for multi-view 3D human pose estimation based on new learnable triangulation methods that combine 3D information from multiple 2D views.
Ranked #2 on
3D Human Pose Estimation
on Human3.6M
Instance Segmentation of Biological Images Using Harmonic Embeddings
We present a new instance segmentation approach tailored to biological images, where instances may correspond to individual cells, organisms or plant parts.
Hyperbolic Image Embeddings
Computer vision tasks such as image classification, image retrieval and few-shot learning are currently dominated by Euclidean and spherical embeddings, so that the final decisions about class belongings or the degree of similarity are made using linear hyperplanes, Euclidean distances, or spherical geodesic distances (cosine similarity).
Deep Neural Networks with Box Convolutions
Box filters computed using integral images have been part of the computer vision toolset for a long time.
Coordinate-based Texture Inpainting for Pose-Guided Image Generation
Since the input photograph always observes only a part of the surface, we suggest a new inpainting method that completes the texture of the human body.
Image Manipulation with Perceptual Discriminators
The new architecture, that we call a perceptual discriminator, embeds the convolutional parts of a pre-trained deep classification network inside the discriminator network.
Instance Segmentation by Deep Coloring
We propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation.
Latent Convolutional Models
The learning process provides a latent embedding for every image in the training dataset, as well as a deep convolutional network that maps the latent space to the image space.
Impostor Networks for Fast Fine-Grained Recognition
In this work we introduce impostor networks, an architecture that allows to perform fine-grained recognition with high accuracy and using a light-weight convolutional network, making it particularly suitable for fine-grained applications on low-power and non-GPU enabled platforms.
Deep Image Prior
In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning.
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
AnnArbor: Approximate Nearest Neighbors Using Arborescence Coding
To compress large datasets of high-dimensional descriptors, modern quantization schemes learn multiple codebooks and then represent individual descriptors as combinations of codewords.
Product Split Trees
In this work, we introduce a new kind of spatial partition trees for efficient nearest-neighbor search.
It Takes (Only) Two: Adversarial Generator-Encoder Networks
Unlike previous hybrids of autoencoders and adversarial networks, the adversarial game in our approach is set up directly between the encoder and the generator, and no external mappings are trained in the process of learning.
Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models
We present a new deep learning architecture (called Kd-network) that is designed for 3D model recognition tasks and works with unstructured point clouds.
Ranked #50 on
3D Part Segmentation
on ShapeNet-Part
Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis
The recent work of Gatys et al., who characterized the style of an image by the statistics of convolutional neural network filters, ignited a renewed interest in the texture generation and image stylization problems.
Parsing Images of Overlapping Organisms with Deep Singling-Out Networks
This work is motivated by the mostly unsolved task of parsing biological images with multiple overlapping articulated model organisms (such as worms or larvae).
End-to-end Learning of Cost-Volume Aggregation for Real-time Dense Stereo
We present a new deep learning-based approach for dense stereo matching.
Learnable Visual Markers
We propose a new approach to designing visual markers (analogous to QR-codes, markers for augmented reality, and robotic fiducial tags) based on the advances in deep generative networks.
Instance Normalization: The Missing Ingredient for Fast Stylization
It this paper we revisit the fast stylization method introduced in Ulyanov et.
DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation
In this work, we consider the task of generating highly-realistic images of a given face with a redirected gaze.
Pairwise Quantization
The proposed approach proceeds by finding a linear transformation of the data that effectively reduces the minimization of the pairwise distortions to the minimization of individual reconstruction errors.
Efficient Indexing of Billion-Scale Datasets of Deep Descriptors
In this paper, we introduce a new dataset of one billion descriptors based on DNNs and reveal the relative inefficiency of IMI-based indexing for such descriptors compared to SIFT data.
Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
Gatys et al. recently demonstrated that deep networks can generate beautiful textures and stylized images from a single texture example.
Multiregion Bilinear Convolutional Neural Networks for Person Re-Identification
In this work we propose a new architecture for person re-identification.
Aggregating Local Deep Features for Image Retrieval
Several recent works have shown that image descriptors produced by deep convolutional neural networks provide state-of-the-art performance for image classification and retrieval problems.
Aggregating Deep Convolutional Features for Image Retrieval
In this paper we investigate possible ways to aggregate local deep features to produce compact global descriptors for image retrieval.
Fast ConvNets Using Group-wise Brain Damage
We revisit the idea of brain damage, i. e. the pruning of the coefficients of a neural network, and suggest how brain damage can be modified and used to speedup convolutional layers.
Learning To Look Up: Realtime Monocular Gaze Correction Using Machine Learning
We revisit the well-known problem of gaze correction and present a solution based on supervised machine learning.
Tree Quantization for Large-Scale Similarity Search and Classification
We propose a new vector encoding scheme (tree quantization) that obtains lossy compact codes for high-dimensional vectors via tree-based dynamic programming.
Domain-Adversarial Training of Neural Networks
Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.
Ranked #2 on
Domain Adaptation
on Synth Digits-to-SVHN
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
We propose a simple two-step approach for speeding up convolution layers within large convolutional neural networks based on tensor decomposition and discriminative fine-tuning.
Unsupervised Domain Adaptation by Backpropagation
Here, we propose a new approach to domain adaptation in deep architectures that can be trained on large amount of labeled data from the source domain and large amount of unlabeled data from the target domain (no labeled target-domain data is necessary).
Ranked #1 on
Domain Adaptation
on UCF-to-Olympic
$ N^4 $-Fields: Neural Network Nearest Neighbor Fields for Image Transforms
We propose a new architecture for difficult image processing operations, such as natural edge detection or thin object segmentation.
Additive Quantization for Extreme Vector Compression
We introduce a new compression scheme for high-dimensional vectors that approximates the vectors using sums of M codewords coming from M different codebooks.
Neural Codes for Image Retrieval
In the experiments with several standard retrieval benchmarks, we establish that neural codes perform competitively even when the convolutional neural network has been trained for an unrelated classification task (e. g.\ Image-Net).
Improving Bilayer Product Quantization for Billion-Scale Approximate Nearest Neighbors in High Dimensions
Here we introduce and evaluate two approximate nearest neighbor search systems that both exploit the synergy of product quantization processes in a more efficient way.
Learning to Detect Partially Overlapping Instances
For example, our detector can pick a region containing two or three object instances, while assigning such region an appropriate label.
Pylon Model for Semantic Segmentation
Often, the random field is applied over a flat partitioning of the image into non-intersecting elements, such as pixels or super-pixels.
Learning To Count Objects in Images
Learning to infer such density can be formulated as a minimization of a regularized risk quadratic cost function.
