Search Results for author: Lourdes Agapito

Found 33 papers, 14 papers with code

HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion

1 code implementation10 May 2023 Mustafa Işık, Martin Rünz, Markos Georgopoulos, Taras Khakhulin, Jonathan Starck, Lourdes Agapito, Matthias Nießner

To close the gap to production-level quality, we introduce HumanRF, a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints.

Motion Synthesis Novel View Synthesis +1

Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM

1 code implementation CVPR 2023 Hengyi Wang, Jingwen Wang, Lourdes Agapito

We present Co-SLAM, a neural RGB-D SLAM system based on a hybrid representation, that performs robust camera tracking and high-fidelity surface reconstruction in real time.

Surface Reconstruction

GNPM: Geometric-Aware Neural Parametric Models

no code implementations21 Sep 2022 Mirgahney Mohamed, Lourdes Agapito

We propose Geometric Neural Parametric Models (GNPM), a learned parametric model that takes into account the local structure of data to learn disentangled shape and pose latent spaces of 4D dynamics, using a geometric-aware architecture on point clouds.

Pose Transfer

GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction

1 code implementation29 Jun 2022 Jingwen Wang, Tymoteusz Bleja, Lourdes Agapito

We present GO-Surf, a direct feature grid optimization method for accurate and fast surface reconstruction from RGB-D sequences.

Surface Reconstruction

Bimodal Camera Pose Prediction for Endoscopy

1 code implementation11 Apr 2022 Anita Rau, Binod Bhattarai, Lourdes Agapito, Danail Stoyanov

Deducing the 3D structure of endoscopic scenes from images remains extremely challenging.

Pose Estimation Pose Prediction +1

Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings

no code implementations9 Dec 2021 Mel Vecerik, Jackie Kay, Raia Hadsell, Lourdes Agapito, Jon Scholz

Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics.

Keypoint Detection Object Tracking

CodeNeRF: Disentangled Neural Radiance Fields for Object Categories

1 code implementation ICCV 2021 Wonbong Jang, Lourdes Agapito

At test time, given a single unposed image of an unseen object, CodeNeRF jointly estimates camera viewpoint, and shape and appearance codes via optimization.

DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

1 code implementation21 Aug 2021 Jingwen Wang, Martin Rünz, Lourdes Agapito

We propose DSP-SLAM, an object-oriented SLAM system that builds a rich and accurate joint map of dense 3D models for foreground objects, and sparse landmark points to represent the background.

3D Object Reconstruction Object SLAM +1

Multi-person Implicit Reconstruction from a Single Image

no code implementations CVPR 2021 Armin Mustafa, Akin Caliskan, Lourdes Agapito, Adrian Hilton

We present a new end-to-end learning framework to obtain detailed and spatially coherent reconstructions of multiple people from a single image.

3D Human Reconstruction

SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera

1 code implementation2 Nov 2020 Denis Tome, Thiemo Alldieck, Patrick Peluse, Gerard Pons-Moll, Lourdes Agapito, Hernan Badino, Fernando de la Torre

The quantitative evaluation, on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric approaches.

Egocentric Pose Estimation Pose Estimation

S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency

no code implementations30 Sep 2020 Mel Vecerik, Jean-Baptiste Regli, Oleg Sushkov, David Barker, Rugile Pevceviciute, Thomas Rothörl, Christopher Schuster, Raia Hadsell, Lourdes Agapito, Jonathan Scholz

In this work we advocate semantic 3D keypoints as a visual representation, and present a semi-supervised training objective that can allow instance or category-level keypoints to be trained to 1-5 millimeter-accuracy with minimal supervision.

Image Reconstruction Representation Learning

FroDO: From Detections to 3D Objects

no code implementations11 May 2020 Kejie Li, Martin Rünz, Meng Tang, Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe

We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers object location, pose and shape in a coarse-to-fine manner.

3D Reconstruction Object Reconstruction +1

xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera

no code implementations ICCV 2019 Denis Tome, Patrick Peluse, Lourdes Agapito, Hernan Badino

Our quantitative evaluation, both on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric pose estimation approaches.

Egocentric Pose Estimation Pose Estimation

3D Pick & Mix: Object Part Blending in Joint Shape and Image Manifolds

no code implementations2 Nov 2018 Adrian Penate-Sanchez, Lourdes Agapito

We present 3D Pick & Mix, a new 3D shape retrieval system that provides users with a new level of freedom to explore 3D shape and Internet image collections by introducing the ability to reason about objects at the level of their constituent parts.

3D Shape Classification 3D Shape Retrieval +1

MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects

1 code implementation24 Apr 2018 Martin Rünz, Maud Buffier, Lourdes Agapito

We present MaskFusion, a real-time, object-aware, semantic and dynamic RGB-D SLAM system that goes beyond traditional systems which output a purely geometric map of a static scene.

Object Recognition Object SLAM +2

Training VAEs Under Structured Residuals

1 code implementation3 Apr 2018 Garoe Dorta, Sara Vicente, Lourdes Agapito, Neill D. F. Campbell, Ivor Simpson

This paper demonstrates a novel scheme to incorporate a structured Gaussian likelihood prediction network within the VAE that allows the residual correlations to be modeled.

Structured Uncertainty Prediction Networks

1 code implementation CVPR 2018 Garoe Dorta, Sara Vicente, Lourdes Agapito, Neill D. F. Campbell, Ivor Simpson

This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image.

Image Denoising

Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading

no code implementations4 Aug 2017 Qi Liu-Yin, Rui Yu, Lourdes Agapito, Andrew Fitzgibbon, Chris Russell

We demonstrate the use of shape-from-shading (SfS) to improve both the quality and the robustness of 3D reconstruction of dynamic objects captured by a single camera.

3D Reconstruction Object Tracking

Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects

1 code implementation20 Jun 2017 Martin Rünz, Lourdes Agapito

In this paper we introduce Co-Fusion, a dense SLAM system that takes a live stream of RGB-D images as input and segments the scene into different objects (using either motion or semantic cues) while simultaneously tracking and reconstructing their 3D shape in real time.

Instance Segmentation Object SLAM +1

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

11 code implementations CVPR 2017 Denis Tome, Chris Russell, Lourdes Agapito

We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks.

3D Pose Estimation Monocular 3D Human Pose Estimation +1

Direct, Dense, and Deformable: Template-Based Non-Rigid 3D Reconstruction From RGB Video

no code implementations ICCV 2015 Rui Yu, Chris Russell, Neill D. F. Campbell, Lourdes Agapito

In contrast, our method makes use of a single RGB video as input; it can capture the deformations of generic shapes; and the depth estimation is dense, per-pixel and direct.

3D Reconstruction Depth Estimation +1

Solving Jigsaw Puzzles with Linear Programming

no code implementations13 Nov 2015 Rui Yu, Chris Russell, Lourdes Agapito

We propose a novel Linear Program (LP) based formula- tion for solving jigsaw puzzles.

Part-Based Modelling of Compound Scenes From Images

no code implementations CVPR 2015 Anton van den Hengel, Chris Russell, Anthony Dick, John Bastian, Daniel Pooley, Lachlan Fleming, Lourdes Agapito

We propose a method to recover the structure of a compound scene from multiple silhouettes.

Lifting Object Detection Datasets into 3D

no code implementations22 Mar 2015 Joao Carreira, Sara Vicente, Lourdes Agapito, Jorge Batista

In particular, acquiring ground truth 3D shapes of objects pictured in 2D images remains a challenging feat and this has hampered progress in recognition-based object reconstruction from a single image.

3D Reconstruction object-detection +3

Good Vibrations: A Modal Analysis Approach for Sequential Non-Rigid Structure from Motion

no code implementations CVPR 2014 Antonio Agudo, Lourdes Agapito, Begona Calvo, Jose M. M. Montiel

We propose an online solution to non-rigid structure from motion that performs camera pose and 3D shape estimation of highly deformable surfaces on a frame-by-frame basis.

Reconstructing PASCAL VOC

no code implementations CVPR 2014 Sara Vicente, Joao Carreira, Lourdes Agapito, Jorge Batista

We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations.

Learning a Manifold as an Atlas

no code implementations CVPR 2013 Nikolaos Pitelis, Chris Russell, Lourdes Agapito

In this work, we return to the underlying mathematical definition of a manifold and directly characterise learning a manifold as finding an atlas, or a set of overlapping charts, that accurately describe local structure.

3D Reconstruction

Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video

no code implementations CVPR 2013 Ravi Garg, Anastasios Roussos, Lourdes Agapito

This paper offers the first variational approach to the problem of dense 3D reconstruction of non-rigid surfaces from a monocular video sequence.

3D Reconstruction

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