Adrian Lopez-Rodriguez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Adrian Lopez-Rodriguez has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Krystian Mikolajczyk
Imperial College London
5 shared publications - Benjamin Busam
Technical University of Munich
2 shared publications - Francesc Moreno-Noguer
Institut de Robòtica i Informàtica Industrial CSIC-UPC
2 shared publications - Alvaro Budria
Institut de Robòtica i Informàtica Industrial (CSIC-UPC)
1 shared publication - Antonio Agudo
Institut de Robòtica i Informàtica Industrial, CSIC-UPC
1 shared publication - Fan Zhang
Personal Robotics Lab, Imperial College London, London, U.K.
1 shared publication
Latest Publications
- 8 December 2024
- Published by Springer Nature
- p. 255-277
InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video
- 8 December 2024
- Published by Springer Nature
- p. 255-277
InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video
- Open Access
- 10 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 147-153
Grasp-Oriented Fine-grained Cloth Segmentation without Real Supervision
- 10 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 147-153
Open AccessGrasp-Oriented Fine-grained Cloth Segmentation without Real Supervision
- Open Access
- 16 December 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (3) , 796-812
Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data
Depth completion aims to predict a dense depth map from a sparse depth input. The acquisition of dense ground-truth annotations for depth completion settings can be difficult and, at the same time, a significant domain gap between real LiDAR measurements and synthetic data has prevented from successful training of models in virtual settings. We propose a domain adaptation approach for sparse-to-dense depth completion that is trained from synthetic data, without annotations in the real domain or additional sensors. Our approach simulates the real sensor noise in an RGB + LiDAR set-up, and consists of three modules: simulating the real LiDAR input in the synthetic domain via projections, filtering the real noisy LiDAR for supervision and adapting the synthetic RGB image using a CycleGAN approach. We extensively evaluate these modules in the KITTI depth completion benchmark.
- 16 December 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (3) , 796-812
Open AccessProject to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data
Depth completion aims to predict a dense depth map from a sparse depth input. The acquisition of dense ground-truth annotations for depth completion settings can be difficult and, at the same time, a significant domain gap between real LiDAR measurements and synthetic data has prevented from successful training of models in virtual settings. We propose a domain adaptation approach for sparse-to-dense depth completion that is trained from synthetic data, without annotations in the real domain or additional sensors. Our approach simulates the real sensor noise in an RGB + LiDAR set-up, and consists of three modules: simulating the real LiDAR input in the synthetic domain via projections, filtering the real noisy LiDAR for supervision and adapting the synthetic RGB image using a CycleGAN approach. We extensively evaluate these modules in the KITTI depth completion benchmark.
- Open Access
- 15 December 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (3) , 752-771
DESC: Domain Adaptation for Depth Estimation via Semantic Consistency
Accurate real depth annotations are difficult to acquire, needing the use of special devices such as a LiDAR sensor. Self-supervised methods try to overcome this problem by processing video or stereo sequences, which may not always be available. Instead, in this paper, we propose a domain adaptation approach to train a monocular depth estimation model using a fully-annotated source dataset and a non-annotated target dataset. We bridge the domain gap by leveraging semantic predictions and low-level edge features to provide guidance for the target domain. We enforce consistency between the main model and a second model trained with semantic segmentation and edge maps, and introduce priors in the form of instance heights. Our approach is evaluated on standard domain adaptation benchmarks for monocular depth estimation and show consistent improvement upon the state-of-the-art. Code available at https://github.com/alopezgit/DESC.
- 15 December 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (3) , 752-771
Open AccessDESC: Domain Adaptation for Depth Estimation via Semantic Consistency
Accurate real depth annotations are difficult to acquire, needing the use of special devices such as a LiDAR sensor. Self-supervised methods try to overcome this problem by processing video or stereo sequences, which may not always be available. Instead, in this paper, we propose a domain adaptation approach to train a monocular depth estimation model using a fully-annotated source dataset and a non-annotated target dataset. We bridge the domain gap by leveraging semantic predictions and low-level edge features to provide guidance for the target domain. We enforce consistency between the main model and a second model trained with semantic segmentation and edge maps, and introduce priors in the form of instance heights. Our approach is evaluated on standard domain adaptation benchmarks for monocular depth estimation and show consistent improvement upon the state-of-the-art. Code available at https://github.com/alopezgit/DESC.
- Open Access
Information Theoretic Representation Distillation
Despite the empirical success of knowledge distillation, current state-of-the-art methods are computationally expensive to train, which makes them difficult to adopt in practice. To address this problem, we introduce two distinct complementary losses inspired by a cheap entropy-like estimator. These losses aim to maximise the correlation and mutual information between the student and teacher representations. Our method incurs significantly less training overheads than other approaches and achieves competitive performance to the state-of-the-art on the knowledge distillation and cross-model transfer tasks. We further demonstrate the effectiveness of our method on a binary distillation task, whereby it leads to a new state-of-the-art for binary quantisation and approaches the performance of a full precision model. Code: www.github.com/roymiles/ITRD
Open AccessInformation Theoretic Representation Distillation
Despite the empirical success of knowledge distillation, current state-of-the-art methods are computationally expensive to train, which makes them difficult to adopt in practice. To address this problem, we introduce two distinct complementary losses inspired by a cheap entropy-like estimator. These losses aim to maximise the correlation and mutual information between the student and teacher representations. Our method incurs significantly less training overheads than other approaches and achieves competitive performance to the state-of-the-art on the knowledge distillation and cross-model transfer tasks. We further demonstrate the effectiveness of our method on a binary distillation task, whereby it leads to a new state-of-the-art for binary quantisation and approaches the performance of a full precision model. Code: www.github.com/roymiles/ITRD
- 27 February 2021
- Published by Springer Nature
- p. 330-348
Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data
- 27 February 2021
- Published by Springer Nature
- p. 330-348
Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data