18 citations · 73 across the 20 of their papers we have counts for
24 papers
DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
Francesco Taioli, Daniel Coelho, Iaroslav Melekhov +4
Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key at…
NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation
Junyuan Fang, Zihan Wang, Yejun Zhang +3
Vision-language models (VLMs) have demonstrated impressive zero-shot transfer capabilities in image-level visual perception tasks. However, they fall short in 3D instance-level seg…
Road Grip Uncertainty Estimation Through Surface State Segmentation
Jyri Maanpää, Julius Pesonen, Iaroslav Melekhov +2
Slippery road conditions pose significant challenges for autonomous driving. Beyond predicting road grip, it is crucial to estimate its uncertainty reliably to ensure safe vehicle…
A Dataset for Semantic Segmentation in the Presence of Unknowns
Zakaria Laskar, Tomas Vojir, Matej Grcic +6
Before deployment in the real-world deep neural networks require thorough evaluation of how they handle both knowns, inputs represented in the training data, and unknowns (anomalie…
AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphones
Xuqian Ren, Matias Turkulainen, Jiepeng Wang +4
Geometric priors are often used to enhance 3D reconstruction. With many smartphones featuring low-resolution depth sensors and the prevalence of off-the-shelf monocular geometry es…
Medical Image Segmentation with SAM-generated Annotations
Iira Häkkinen, Iaroslav Melekhov, Erik Englesson +2
The field of medical image segmentation is hindered by the scarcity of large, publicly available annotated datasets. Not all datasets are made public for privacy reasons, and creat…
Differentiable Product Quantization for Memory Efficient Camera Relocalization
Zakaria Laskar, Iaroslav Melekhov, Assia Benbihi +2
Camera relocalization relies on 3D models of the scene with a large memory footprint that is incompatible with the memory budget of several applications. One solution to reduce the…
Dense Road Surface Grip Map Prediction from Multimodal Image Data
Jyri Maanpää, Julius Pesonen, Heikki Hyyti +5
Slippery road weather conditions are prevalent in many regions and cause a regular risk for traffic. Still, there has been less research on how autonomous vehicles could detect sli…
ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation
Iaroslav Melekhov, Anand Umashankar, Hyeong-Jin Kim +2
We introduce ECLAIR (Extended Classification of Lidar for AI Recognition), a new outdoor large-scale aerial LiDAR dataset designed specifically for advancing research in point clou…
DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing
Matias Turkulainen, Xuqian Ren, Iaroslav Melekhov +3
High-fidelity 3D reconstruction of common indoor scenes is crucial for VR and AR applications. 3D Gaussian splatting, a novel differentiable rendering technique, has achieved state…
HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer
Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov +4
Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local d…
Leveraging Road Area Semantic Segmentation with Auxiliary Steering Task
Jyri Maanpää, Iaroslav Melekhov, Josef Taher +2
Robustness of different pattern recognition methods is one of the key challenges in autonomous driving, especially when driving in the high variety of road environments and weather…
Digging Into Self-Supervised Learning of Feature Descriptors
Iaroslav Melekhov, Zakaria Laskar, Xiaotian Li +2
Fully-supervised CNN-based approaches for learning local image descriptors have shown remarkable results in a wide range of geometric tasks. However, most of them require per-pixel…
Continual Learning for Image-Based Camera Localization
Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov +2
For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene…
Multimodal End-to-End Learning for Autonomous Steering in Adverse Road and Weather Conditions
Jyri Maanpää, Josef Taher, Petri Manninen +3
Autonomous driving is challenging in adverse road and weather conditions in which there might not be lane lines, the road might be covered in snow and the visibility might be poor.…
Image Stylization for Robust Features
Iaroslav Melekhov, Gabriel J. Brostow, Juho Kannala +1
Local features that are robust to both viewpoint and appearance changes are crucial for many computer vision tasks. In this work we investigate if photorealistic image stylization…
Bayesian Feature Pyramid Networks for Automatic Multi-Label Segmentation of Chest X-rays and Assessment of Cardio-Thoratic Ratio
Roman Solovyev, Iaroslav Melekhov, Timo Lesonen +3
Cardiothoratic ratio (CTR) estimated from chest radiographs is a marker indicative of cardiomegaly, the presence of which is in the criteria for heart failure diagnosis. Existing m…
KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks
Aleksei Tiulpin, Iaroslav Melekhov, Simo Saarakkala
This paper addresses the challenge of localization of anatomical landmarks in knee X-ray images at different stages of osteoarthritis (OA). Landmark localization can be viewed as r…
Geometric Image Correspondence Verification by Dense Pixel Matching
Zakaria Laskar, Iaroslav Melekhov, Hamed R. Tavakoli +2
This paper addresses the problem of determining dense pixel correspondences between two images and its application to geometric correspondence verification in image retrieval. The…
DGC-Net: Dense Geometric Correspondence Network
Iaroslav Melekhov, Aleksei Tiulpin, Torsten Sattler +3
This paper addresses the challenge of dense pixel correspondence estimation between two images. This problem is closely related to optical flow estimation task where ConvNets (CNNs…
Image Patch Matching Using Convolutional Descriptors with Euclidean Distance
Iaroslav Melekhov, Juho Kannala, Esa Rahtu
In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is…
Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network
Zakaria Laskar, Iaroslav Melekhov, Surya Kalia +1
We propose a new deep learning based approach for camera relocalization. Our approach localizes a given query image by using a convolutional neural network (CNN) for first retrievi…
Image-based Localization using Hourglass Networks
Iaroslav Melekhov, Juha Ylioinas, Juho Kannala +1
In this paper, we propose an encoder-decoder convolutional neural network (CNN) architecture for estimating camera pose (orientation and location) from a single RGB-image. The arch…
Relative Camera Pose Estimation Using Convolutional Neural Networks
Iaroslav Melekhov, Juha Ylioinas, Juho Kannala +1
This paper presents a convolutional neural network based approach for estimating the relative pose between two cameras. The proposed network takes RGB images from both cameras as i…