no code implementations • 4 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.
no code implementations • 22 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.
no code implementations • 13 Nov 2015 • Rui Yu, Chris Russell, Lourdes Agapito
We propose a novel Linear Program (LP) based formula- tion for solving jigsaw puzzles.
no code implementations • 2 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.
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.
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.
no code implementations • CVPR 2013 • Parthipan Siva, Chris Russell, Tao Xiang, Lourdes Agapito
We propose a principled probabilistic formulation of object saliency as a sampling problem.
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.
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.
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.
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.
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.
Ranked #7 on Egocentric Pose Estimation on GlobalEgoMocap Test Dataset (using extra training data)
no code implementations • 11 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.
no code implementations • CVPR 2018 • Michael Firman, Neill D. F. Campbell, Lourdes Agapito, Gabriel J. Brostow
For a single input, we learn to predict a range of possible answers.
no code implementations • 30 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.
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.
no code implementations • 9 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.
no code implementations • 21 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.
no code implementations • CVPR 2023 • Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos, Martin Rünz, Lourdes Agapito, Matthias Nießner
We propose a novel 3D morphable model for complete human heads based on hybrid neural fields.
1 code implementation • 28 Jun 2023 • Jingwen Wang, Juan Tarrio, Lourdes Agapito, Pablo F. Alcantarilla, Alexander Vakhitov
We present a new methodology for real-time semantic mapping from RGB-D sequences that combines a 2D neural network and a 3D network based on a SLAM system with 3D occupancy mapping.
no code implementations • 30 Aug 2023 • Mel Vecerik, Carl Doersch, Yi Yang, Todor Davchev, Yusuf Aytar, Guangyao Zhou, Raia Hadsell, Lourdes Agapito, Jon Scholz
For robots to be useful outside labs and specialized factories we need a way to teach them new useful behaviors quickly.
no code implementations • 14 Nov 2023 • Mirgahney Mohamed, Lourdes Agapito
We depart from current neural non-rigid surface reconstruction models by designing the canonical representation as a learned feature grid which leads to faster and more accurate surface reconstruction than competing approaches that use a single MLP.
no code implementations • 11 Dec 2023 • Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos, Martin Rünz, Lourdes Agapito, Matthias Nießner
We present Monocular Neural Parametric Head Models (MonoNPHM) for dynamic 3D head reconstructions from monocular RGB videos.
no code implementations • 13 Dec 2023 • Wonbong Jang, Lourdes Agapito
We propose NViST, a transformer-based model for efficient and generalizable novel-view synthesis from a single image for real-world scenes.
1 code implementation • 2 Oct 2023 • Anita Rau, Binod Bhattarai, Lourdes Agapito, Danail Stoyanov
Colorectal cancer remains one of the deadliest cancers in the world.
1 code implementation • 4 Aug 2018 • Denis Tome, Matteo Toso, Lourdes Agapito, Chris Russell
We propose a CNN-based approach for multi-camera markerless motion capture of the human body.
Ranked #201 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 15 Sep 2022 • Denis Hadjivelichkov, Sicelukwanda Zwane, Marc Peter Deisenroth, Lourdes Agapito, Dimitrios Kanoulas
In this work, we tackle one-shot visual search of object parts.
2 code implementations • 3 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.
2 code implementations • 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.
1 code implementation • 11 Apr 2022 • Anita Rau, Binod Bhattarai, Lourdes Agapito, Danail Stoyanov
Deducing the 3D structure of endoscopic scenes from images is exceedingly challenging.
1 code implementation • 2 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.
1 code implementation • 1 Apr 2024 • David Svitov, Pietro Morerio, Lourdes Agapito, Alessio Del Bue
We demonstrate the effectiveness of our approach on two open datasets: SnapshotPeople and X-Humans.
1 code implementation • 1 Dec 2023 • Hengyi Wang, Jingwen Wang, Lourdes Agapito
Thanks to the expressiveness of neural representations, prior works can accurately capture the motion and achieve high-fidelity reconstruction of the target object.
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.
1 code implementation • 29 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.
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.
1 code implementation • 10 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.
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.
Ranked #22 on Weakly-supervised 3D Human Pose Estimation on Human3.6M
1 code implementation • 20 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.
1 code implementation • 21 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.
1 code implementation • 24 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.