64 citations · 343 across the 48 of their papers we have counts for
12 papers · 1 filter
Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images
Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo +2
We address the problem of multi-person 3D body pose and shape estimation from a single image. While this problem can be addressed by applying single-person approaches multiple time…
PhysXNet: A Customizable Approach for LearningCloth Dynamics on Dressed People
Jordi Sanchez-Riera, Albert Pumarola, Francesc Moreno-Noguer
We introduce PhysXNet, a learning-based approach to predict the dynamics of deformable clothes given 3D skeleton motion sequences of humans wearing these clothes. The proposed mode…
Grasp-Oriented Fine-grained Cloth Segmentation without Real Supervision
Ruijie Ren, Mohit Gurnani Rajesh, Jordi Sanchez-Riera +6
Automatically detecting graspable regions from a single depth image is a key ingredient in cloth manipulation. The large variability of cloth deformations has motivated most of the…
An Adaptable Approach to Learn Realistic Legged Locomotion without Examples
Daniel Ordonez-Apraez, Antonio Agudo, Francesc Moreno-Noguer +1
Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are…
Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representations
Jianxiong Shen, Adria Ruiz, Antonio Agudo +1
Neural Radiance Fields (NeRF) has become a popular framework for learning implicit 3D representations and addressing different tasks such as novel-view synthesis or depth-map estim…
SIDER: Single-Image Neural Optimization for Facial Geometric Detail Recovery
Aggelina Chatziagapi, ShahRukh Athar, Francesc Moreno-Noguer +1
We present SIDER(Single-Image neural optimization for facial geometric DEtail Recovery), a novel photometric optimization method that recovers detailed facial geometry from a singl…
H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction
Eduard Ramon, Gil Triginer, Janna Escur +4
Recent learning approaches that implicitly represent surface geometry using coordinate-based neural representations have shown impressive results in the problem of multi-view 3D re…
Uncertainty-Aware Camera Pose Estimation from Points and Lines
Alexander Vakhitov, Luis Ferraz Colomina, Antonio Agudo +1
Perspective-n-Point-and-Line (PPL) algorithms aim at fast, accurate, and robust camera localization with respect to a 3D model from 2D-3D feature correspondences, being a major…
Multi-Person Extreme Motion Prediction
Wen Guo, Xiaoyu Bie, Xavier Alameda-Pineda +1
Human motion prediction aims to forecast future poses given a sequence of past 3D skeletons. While this problem has recently received increasing attention, it has mostly been tackl…
SMPLicit: Topology-aware Generative Model for Clothed People
Enric Corona, Albert Pumarola, Guillem Alenyà +2
In this paper we introduce SMPLicit, a novel generative model to jointly represent body pose, shape and clothing geometry. In contrast to existing learning-based approaches that re…
AVATAR: Blender add-on for fast creation of 3D human models
Jordi Sanchez-Riera, Aniol Civit, Marta Altarriba +1
Create an articulated and realistic human 3D model is a complicated task, not only get a model with the right body proportions but also to the whole process of rigging the model wi…
3D Human Pose, Shape and Texture from Low-Resolution Images and Videos
Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer +2
3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution i…