Search Results for author:
Found 48 papers, 17 papers with code
BLSM: A Bone-Level Skinned Model of the Human Mesh
We introduce BLSM, a bone-level skinned model of the human body mesh where bone scales are set prior to template synthesis, rather than the common, inverse practice.
Deformably-Scaled Transposed Convolution
Transposed convolution is crucial for generating high-resolution outputs, yet has received little attention compared to convolution layers.
Beyond Deterministic Translation for Unsupervised Domain Adaptation
In this work we challenge the common approach of using a one-to-one mapping ('translation') between the source and target domains in unsupervised domain adaptation (UDA).
Unsupervised Domain Adaptation with Semantic Consistency across Heterogeneous Modalities for MRI Prostate Lesion Segmentation
Firstly, we introduce a semantic cycle-consistency loss in the source domain to ensure that the translation preserves the semantics.
To The Point: Correspondence-driven monocular 3D category reconstruction
We present To The Point (TTP), a method for reconstructing 3D objects from a single image using 2D to 3D correspondences learned from weak supervision.
Learning monocular 3D reconstruction of articulated categories from motion
Monocular 3D reconstruction of articulated object categories is challenging due to the lack of training data and the inherent ill-posedness of the problem.
Harnessing Uncertainty in Domain Adaptation for MRI Prostate Lesion Segmentation
Domain adaptation methods partially mitigate this problem by translating training data from a related source domain to a novel target domain, but typically assume that a one-to-one translation is possible.
Holistic Multi-View Building Analysis in the Wild with Projection Pooling
To this end, we introduce a new benchmarking dataset, consisting of 49426 images (top-view and street-view) of 9674 buildings.
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh reconstruction loss.
Going Deeper with Lean Point Networks
By combining these blocks, we design wider and deeper point-based architectures.
Deep Learning Enhanced Extended Depth-of-Field for Thick Blood-Film Malaria High-Throughput Microscopy
Here we address the problem of Extended Depth-of-Field (EDoF) in thick blood film microscopy for rapid automated malaria diagnosis.
Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cues
DensePose supersedes traditional landmark detectors by densely mapping image pixels to body surface coordinates.
Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion
In this work we introduce Lifting Autoencoders, a generative 3D surface-based model of object categories.
Attentive Single-Tasking of Multiple Tasks
In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as "single-tasking multiple tasks".
MultiGrain: a unified image embedding for classes and instances
When fed to a linear classifier, the learned embeddings provide state-of-the-art classification accuracy.
Ranked #1 on
Image Retrieval
on INRIA Holidays
Dense Pose Transfer
In this work we integrate ideas from surface-based modeling with neural synthesis: we propose a combination of surface-based pose estimation and deep generative models that allows us to perform accurate pose transfer, i. e. synthesize a new image of a person based on a single image of that person and the image of a pose donor.
Deeper Image Quality Transfer: Training Low-Memory Neural Networks for 3D Images
In this paper we address the memory demands that come with the processing of 3-dimensional, high-resolution, multi-channeled medical images in deep learning.
Deep Spatio-Temporal Random Fields for Efficient Video Segmentation
In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time.
Ranked #6 on
Semantic Segmentation
on CamVid
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner.
Ranked #9 on
Unsupervised Facial Landmark Detection
on MAFL
DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
We define the regression task in terms of the intrinsic, U-V coordinates of a 3D deformable model that is brought into correspondence with image instances at training time.
DensePose: Dense Human Pose Estimation In The Wild
In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation.
Ranked #2 on
Pose Estimation
on DensePose-COCO
Learning Filterbanks from Raw Speech for Phone Recognition
We train a bank of complex filters that operates on the raw waveform and is fed into a convolutional neural network for end-to-end phone recognition.
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings
In this work we introduce a structured prediction model that endows the Deep Gaussian Conditional Random Field (G-CRF) with a densely connected graph structure.
Segmentation-Aware Convolutional Networks Using Local Attention Masks
We introduce an approach to integrate segmentation information within a convolutional neural network (CNN).
Mass Displacement Networks
Despite the large improvements in performance attained by using deep learning in computer vision, one can often further improve results with some additional post-processing that exploits the geometric nature of the underlying task.
Ubernet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory
In this work we train in an end-to-end manner a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture.
Face Normals "In-The-Wild" Using Fully Convolutional Networks
In this work we pursue a data-driven approach to the problem of estimating surface normals from a single intensity image, focusing in particular on human faces.
DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
As such our network can provide useful correspondence information as a stand-alone system, while when used as an initialization for Statistical Deformable Models we obtain landmark localization results that largely outperform the current state-of-the-art on the challenging 300W benchmark.
Deep, Dense, and Low-Rank Gaussian Conditional Random Fields
In this work we introduce a fully-connected graph structure in the Deep Gaussian Conditional Random Field (G-CRF) model.
UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory
In this work we introduce a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture that is trained end-to-end.
Prior-based Coregistration and Cosegmentation
We propose a modular and scalable framework for dense coregistration and cosegmentation with two key characteristics: first, we substitute ground truth data with the semantic map output of a classifier; second, we combine this output with population deformable registration to improve both alignment and segmentation.
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales.
Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
In this work we propose a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields (G-CRF) with Deep Learning: (a) our structured prediction task has a unique global optimum that is obtained exactly from the solution of a linear system (b) the gradients of our model parameters are analytically computed using closed form expressions, in contrast to the memory-demanding contemporary deep structured prediction approaches that rely on back-propagation-through-time, (c) our pairwise terms do not have to be simple hand-crafted expressions, as in the line of works building on the DenseCRF, but can rather be `discovered' from data through deep architectures, and (d) out system can trained in an end-to-end manner.
Ranked #29 on
Semantic Segmentation
on PASCAL VOC 2012 test
Sub-cortical brain structure segmentation using F-CNN's
In this paper we propose a deep learning approach for segmenting sub-cortical structures of the human brain in Magnetic Resonance (MR) image data.
Discriminative Learning of Deep Convolutional Feature Point Descriptors
Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e. g. SIFT.
Ranked #2 on
Satellite Image Classification
on SAT-4
Pushing the Boundaries of Boundary Detection using Deep Learning
In this work we show that adapting Deep Convolutional Neural Network training to the task of boundary detection can result in substantial improvements over the current state-of-the-art in boundary detection.
Learning Dense Convolutional Embeddings for Semantic Segmentation
That is, for any two pixels on the same object, the embeddings are trained to be similar; for any pair that straddles an object boundary, the embeddings are trained to be dissimilar.
Deep filter banks for texture recognition, description, and segmentation
Visual textures have played a key role in image understanding because they convey important semantics of images, and because texture representations that pool local image descriptors in an orderless manner have had a tremendous impact in diverse applications.
Modeling Local and Global Deformations in Deep Learning: Epitomic Convolution, Multiple Instance Learning, and Sliding Window Detection
Deep Convolutional Neural Networks (DCNNs) achieve invariance to domain transformations (deformations) by using multiple 'max-pooling' (MP) layers.
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
This is due to the very invariance properties that make DCNNs good for high level tasks.
Ranked #3 on
Scene Segmentation
on SUN-RGBD
Fracking Deep Convolutional Image Descriptors
In this paper we propose a novel framework for learning local image descriptors in a discriminative manner.
Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection
Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment.
Understanding Objects in Detail with Fine-Grained Attributes
We show that the collected data can be used to study the relation between part detection and attribute prediction by diagnosing the performance of classifiers that pool information from different parts of an object.
Fast and Exact: ADMM-Based Discriminative Shape Segmentation with Loopy Part Models
In this work we use loopy part models to segment ensembles of organs in medical images.
Segmentation-aware Deformable Part Models
In this work we propose a technique to combine bottom-up segmentation, coming in the form of SLIC superpixels, with sliding window detectors, such as Deformable Part Models (DPMs).
Describing Textures in the Wild
Patterns and textures are defining characteristics of many natural objects: a shirt can be striped, the wings of a butterfly can be veined, and the skin of an animal can be scaly.
Dense Segmentation-Aware Descriptors
In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes.
Rapid Deformable Object Detection using Dual-Tree Branch-and-Bound
For the problem of finding the strongest category in an image this results in up to a 100-fold speedup.
