arXiv subjects

Călin-Adrian Popa

Publications and source records attributed to Călin-Adrian Popa.

5 recordsLinked to original sources

arXiv2026

JEPADepth: Masked Predictive Representation Learning for Self-Supervised Monocular Depth Estimation

Self-supervised monocular depth estimation typically relies on photometric reconstruction losses that couple depth, pose, and appearance assumptions. In this paper, we propose JEPADepth, a self-supervised monocular depth framework that incorporates a complementary training objective inspired by Image Joint-Embedding Predictive Architectures (I-JEPA) for self-supervised depth learning. Our method augments a standard photometric pipeline with a masked prediction loss computed in the representation space of a pretrained DINOv3 Vision Transformer encoder. A predictor infers target-region embeddings from visible context-region embeddings under structured masking, and is discarded along with the target encoder at inference time, adding no deployment cost. On KITTI, adding the JEPA objective consistently improves performance over the same DINOv3-based photometric baseline, without changing the inference-time architecture. Compared to prior monocular self-supervised methods, JEPADepth is competitive with state-of-the-art transformer-based approaches and outperforms strong CNN-based baselines on the standard benchmark. In zero-shot transfer (trained on KITTI and evaluated without fine-tuning), JEPADepth achieves the best or near-best performance among the compared methods on both Make3D and Cityscapes across multiple metrics.

cs.CV↗

arXiv2025

FPC-Net: Revisiting SuperPoint with Descriptor-Free Keypoint Detection via Feature Pyramids and Consistency-Based Implicit Matching

The extraction and matching of interest points are fundamental to many geometric computer vision tasks. Traditionally, matching is performed by assigning descriptors to interest points and identifying correspondences based on descriptor similarity. This work introduces a technique where interest points are inherently associated during detection, eliminating the need for computing, storing, transmitting, or matching descriptors. Although the matching accuracy is marginally lower than that of conventional approaches, our method completely eliminates the need for descriptors, leading to a drastic reduction in memory usage for localization systems. We assess its effectiveness by comparing it against both classical handcrafted methods and modern learned approaches.

cs.CV↗

arXiv2024

XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images

Reflected or scattered light produce artefacts in astronomical observations that can negatively impact the scientific study. Hence, automated detection of these artefacts is highly beneficial, especially with the increasing amounts of data gathered. Machine learning methods are well-suited to this problem, but currently there is a lack of annotated data to train such approaches to detect artefacts in astronomical observations. In this work, we present a dataset of images from the XMM-Newton space telescope Optical Monitoring camera showing different types of artefacts. We hand-annotated a sample of 1000 images with artefacts which we use to train automated ML methods. We further demonstrate techniques tailored for accurate detection and masking of artefacts using instance segmentation. We adopt a hybrid approach, combining knowledge from both convolutional neural networks (CNNs) and transformer-based models and use their advantages in segmentation. The presented method and dataset will advance artefact detection in astronomical observations by providing a reproducible baseline. All code and data are made available (https://github.com/ESA-Datalabs/XAMI-model and https://github.com/ESA-Datalabs/XAMI-dataset).

cs.CV↗

arXiv2024

MambaDepth: Enhancing Long-range Dependency for Self-Supervised Fine-Structured Monocular Depth Estimation

In the field of self-supervised depth estimation, Convolutional Neural Networks (CNNs) and Transformers have traditionally been dominant. However, both architectures struggle with efficiently handling long-range dependencies due to their local focus or computational demands. To overcome this limitation, we present MambaDepth, a versatile network tailored for self-supervised depth estimation. Drawing inspiration from the strengths of the Mamba architecture, renowned for its adept handling of lengthy sequences and its ability to capture global context efficiently through a State Space Model (SSM), we introduce MambaDepth. This innovative architecture combines the U-Net's effectiveness in self-supervised depth estimation with the advanced capabilities of Mamba. MambaDepth is structured around a purely Mamba-based encoder-decoder framework, incorporating skip connections to maintain spatial information at various levels of the network. This configuration promotes an extensive feature learning process, enabling the capture of fine details and broader contexts within depth maps. Furthermore, we have developed a novel integration technique within the Mamba blocks to facilitate uninterrupted connectivity and information flow between the encoder and decoder components, thereby improving depth accuracy. Comprehensive testing across the established KITTI dataset demonstrates MambaDepth's superiority over leading CNN and Transformer-based models in self-supervised depth estimation task, allowing it to achieve state-of-the-art performance. Moreover, MambaDepth proves its superior generalization capacities on other datasets such as Make3D and Cityscapes. MambaDepth's performance heralds a new era in effective long-range dependency modeling for self-supervised depth estimation.

cs.CV↗

arXiv2013

Averaging on Manifolds by Embedding Algorithm

We will propose a new algorithm for finding critical points of cost functions defined on a differential manifold. We will lift the initial cost function to a manifold that can be embedded in a Riemannian manifold (Euclidean space) and will construct a vector field defined on the ambient space whose restriction to the embedded manifold is the gradient vector field of the lifted cost function. The advantage of this method is that it allows us to do computations in Cartesian coordinates instead of using local coordinates and covariant derivatives on the initial manifold. We will exemplify the algorithm in the case of SO(3) averaging problems and will rediscover a few well known results that appear in literature.

math.OC↗