Related papers: HR-APR: APR-agnostic Framework with Uncertainty Es…

For recovering 3D object poses from 2D images, a prevalent method is to pre-train an over-complete dictionary $\mathcal D=\{B_i\}_i^D$ of 3D basis poses. During testing, the detected 2D pose $Y$ is matched to dictionary by $Y \approx \sum_i…

Camera calibration is a necessity in various tasks including 3D reconstruction, hand-eye coordination for a robotic interaction, autonomous driving, etc. In this work we propose a novel method to predict extrinsic (baseline, pitch, and…

In this work, we propose HE-VPR, a visual place recognition (VPR) framework that incorporates height estimation. Our system decouples height inference from place recognition, allowing both modules to share a frozen DINOv2 backbone. Two…

Visual place recognition techniques based on deep learning, which have imposed themselves as the state-of-the-art in recent years, do not generalize well to environments visually different from the training set. Thus, to achieve top…

Pose-free neural radiance fields (NeRF) aim to train NeRF with unposed multi-view images and it has achieved very impressive success in recent years. Most existing works share the pipeline of training a coarse pose estimator with rendered…

Accurate and robust relative pose estimation is crucial for enabling challenging Active Debris Removal (ADR) missions targeting tumbling derelict satellites such as ESA's ENVISAT. This work presents a complete pipeline integrating advanced…

We propose UAPAR, an Uncertainty-Aware Pedestrian Attribute Recognition framework. To the best of our knowledge, this is the first EDL-based uncertainty-aware framework for pedestrian attribute recognition (PAR). Unlike conventional…

We propose a general self-supervised learning approach for spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings. The model is learned from training episodes, by relying on: a…

Recent advances in deep learning have shown that uncertainty estimation is becoming increasingly important in applications such as medical imaging, natural language processing, and autonomous systems. However, accurately quantifying…

We present a robust method for estimating the facial pose and shape information from a densely annotated facial image. The method relies on Convolutional Point-set Representation (CPR), a carefully designed matrix representation to…

A prior represents a set of beliefs or assumptions about a system, aiding inference and decision-making. In this paper, we introduce the challenge of unsupervised categorical prior learning in pose estimation, where AI models learn a…

Visual Place Recognition (VPR) aims to match query images against a database using visual cues. State-of-the-art methods aggregate features from deep backbones to form global descriptors. Optimal transport-based aggregation methods…

Image super-resolution (SR) is an underdetermined inverse problem, where a large number of plausible high-resolution images can explain the same downsampled image. Most current single image SR methods use empirical risk minimisation, often…

We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video. We integrate a learning-based depth prior, in the form of a convolutional neural network trained for single-image depth estimation,…

The structural re-parameterization (SRP) technique is a novel deep learning technique that achieves interconversion between different network architectures through equivalent parameter transformations. This technique enables the mitigation…

Automated Program Repair (APR) is a fast growing area with numerous new techniques being developed to tackle one of the most challenging software engineering problems. APR techniques have shown promising results, giving us hope that one day…

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

Convolutional neural networks (CNNs) are extremely popular and effective for image classification tasks but tend to be overly confident in their predictions. Various works have sought to quantify uncertainty associated with these models,…

Recent progress in learning-based image compression has demonstrated that end-to-end optimization can substantially outperform traditional codecs by jointly learning compact latent representations and probabilistic entropy models. However,…

The task of Visual Place Recognition (VPR) is to predict the location of a query image from a database of geo-tagged images. Recent studies in VPR have highlighted the significant advantage of employing pre-trained foundation models like…