1 code implementation • 13 Nov 2024 • David Svitov, Pietro Morerio, Lourdes Agapito, Alessio Del Bue
We present billboard Splatting (BBSplat) - a novel approach for 3D scene representation based on textured geometric primitives.
no code implementations • 28 Aug 2024 • Hengyi Wang, Lourdes Agapito
Spann3R then queries this spatial memory to predict the 3D structure of the next frame in a global coordinate system.
no code implementations • 11 Jun 2024 • Mirgahney Mohamed, Harry Jake Cunningham, Marc P. Deisenroth, Lourdes Agapito
We demonstrate the effectiveness of RecMoDiffuse in the temporal modelling of human motion.
no code implementations • 29 May 2024 • Simon Giebenhain, Tobias Kirschstein, Martin Rünz, Lourdes Agapito, Matthias Nießner
In this work, we propose Neural Parametric Gaussian Avatars (NPGA), a data-driven approach to create high-fidelity, controllable avatars from multi-view video recordings.
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.
no code implementations • CVPR 2024 • 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.
no code implementations • CVPR 2024 • 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.
no code implementations • CVPR 2024 • 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.
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.
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.
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.
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.
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.
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.
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 • 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.
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.
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.
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 • 11 Apr 2022 • Anita Rau, Binod Bhattarai, Lourdes Agapito, Danail Stoyanov
Deducing the 3D structure of endoscopic scenes from images is exceedingly challenging.
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.
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 • 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.
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.
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.
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 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 • 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 • 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 • 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.
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 #217 on
3D Human Pose Estimation
on Human3.6M
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.
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.
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.
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.
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
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 • 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 • 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 • 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 • 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 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 • 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 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.