Search Results for author: Nikolaos Sarafianos

Found 13 papers, 2 papers with code

BodyMap: Learning Full-Body Dense Correspondence Map

no code implementations18 May 2022 Anastasia Ianina, Nikolaos Sarafianos, Yuanlu Xu, Ignacio Rocco, Tony Tung

Dense correspondence between humans carries powerful semantic information that can be utilized to solve fundamental problems for full-body understanding such as in-the-wild surface matching, tracking and reconstruction.

Neural Rendering Novel View Synthesis

Animatable Neural Radiance Fields from Monocular RGB-D

no code implementations4 Apr 2022 Tiantian Wang, Nikolaos Sarafianos, Ming-Hsuan Yang, Tony Tung

To tackle this problem, we introduce a novel method to integrate observations across frames and encode the appearance at each individual frame by utilizing the human pose that models the body shape and point clouds which cover partial part of the human as the input.


SPAMs: Structured Implicit Parametric Models

no code implementations20 Jan 2022 Pablo Palafox, Nikolaos Sarafianos, Tony Tung, Angela Dai

We observe that deformable object motion is often semantically structured, and thus propose to learn Structured-implicit PArametric Models (SPAMs) as a deformable object representation that structurally decomposes non-rigid object motion into part-based disentangled representations of shape and pose, with each being represented by deep implicit functions.

Human View Synthesis using a Single Sparse RGB-D Input

no code implementations27 Dec 2021 Phong Nguyen, Nikolaos Sarafianos, Christoph Lassner, Janne Heikkila, Tony Tung

We show our method generates high-quality novel views of synthetic and real human actors given a single sparse RGB-D input.

Neural Rendering Novel View Synthesis

Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing

1 code implementation ICCV 2021 Garvita Tiwari, Nikolaos Sarafianos, Tony Tung, Gerard Pons-Moll

Neural-GIF can be trained on raw 3D scans and reconstructs detailed complex surface geometry and deformations.

Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans

no code implementations CVPR 2021 Bindita Chaudhuri, Nikolaos Sarafianos, Linda Shapiro, Tony Tung

Given a segmentation mask defining the layout of the semantic regions in the texture map, our network generates high-resolution textures with a variety of styles, that are then used for rendering purposes.

Virtual Try-on

On Improving the Generalization of Face Recognition in the Presence of Occlusions

no code implementations11 Jun 2020 Xiang Xu, Nikolaos Sarafianos, Ioannis A. Kakadiaris

In this paper, we address a key limitation of existing 2D face recognition methods: robustness to occlusions.

Face Recognition

Adversarial Representation Learning for Text-to-Image Matching

no code implementations ICCV 2019 Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris

For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem.

Image Captioning Language Modelling +4

Deep Imbalanced Attribute Classification using Visual Attention Aggregation

2 code implementations ECCV 2018 Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris

For many computer vision applications, such as image description and human identification, recognizing the visual attributes of humans is an essential yet challenging problem.

Classification General Classification

Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification

no code implementations19 Sep 2017 Nikolaos Sarafianos, Theodore Giannakopoulos, Christophoros Nikou, Ioannis A. Kakadiaris

In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework.

Classification General Classification

Adaptive SVM+: Learning with Privileged Information for Domain Adaptation

no code implementations30 Aug 2017 Nikolaos Sarafianos, Michalis Vrigkas, Ioannis A. Kakadiaris

Incorporating additional knowledge in the learning process can be beneficial for several computer vision and machine learning tasks.

Domain Adaptation

Curriculum Learning for Multi-Task Classification of Visual Attributes

no code implementations29 Aug 2017 Nikolaos Sarafianos, Theodore Giannakopoulos, Christophoros Nikou, Ioannis A. Kakadiaris

Visual attributes, from simple objects (e. g., backpacks, hats) to soft-biometrics (e. g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification.

Classification General Classification +1

Predicting Privileged Information for Height Estimation

no code implementations9 Feb 2017 Nikolaos Sarafianos, Christophoros Nikou, Ioannis A. Kakadiaris

In this paper, we propose a novel regression-based method for employing privileged information to estimate the height using human metrology.

Cannot find the paper you are looking for? You can Submit a new open access paper.