Adrian Lopez-Rodriguez

Adrian Lopez-Rodriguez

Auto-generated profile, based on publicly available information

Adrian Lopez-Rodriguez

Imperial College London, London, UK

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 December 2022 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
ALAdrian Lopez-Rodriguez
Adrian Lopez-Rodriguez
KMKrystian Mikolajczyk
Krystian Mikolajczyk
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.


16 December 2022 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
ALAdrian Lopez-Rodriguez
Adrian Lopez-Rodriguez
BBBenjamin Busam
Benjamin Busam
KMKrystian Mikolajczyk
Krystian Mikolajczyk
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.

10 March 2023
Verified
Conference Paper
Open access
RRRuijie Ren
Ruijie Ren
MRMohit Gurnani Rajesh
Mohit Gurnani Rajesh
JSJordi Sanchez-Riera
Jordi Sanchez-Riera
ALAdrian Lopez-Rodriguez
Adrian Lopez-Rodriguez
FZFan Zhang
Fan Zhang
FMFrancesc Moreno-Noguer
Francesc Moreno-Noguer

8 December 2024
Verified
Book Chapter
Closed access
PDF file
ABAlvaro Budria
Alvaro Budria
ALAdrian Lopez-Rodriguez
Adrian Lopez-Rodriguez
ÒLÒscar Lorente
Òscar Lorente
FMFrancesc Moreno-Noguer
Francesc Moreno-Noguer

7 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
RMRoy Miles
Roy Miles
ARAdrian Lopez Rodriguez
Adrian Lopez Rodriguez
KMKrystian Mikolajczyk
Krystian Mikolajczyk
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