1.8k citations · 4.6k across the 57 of their papers we have counts for
67 papers
HorizonNet for visual terrain navigation
Bertil Grelsson, Andreas Robinson, Michael Felsberg +1
This paper investigates the problem of position estimation of unmanned surface vessels (USVs) operating in coastal areas or in the archipelago. We propose a position estimation met…
Using Channel Representations in Regularization Terms: A Case Study on Image Diffusion
Christian Heinemann, Freddie Åström, George Baravdish +3
In this work we propose a novel non-linear diffusion filtering approach for images based on their channel representation. To derive the diffusion update scheme we formulate a novel…
A Tensor Variational Formulation of Gradient Energy Total Variation
Freddie Åström, George Baravdish, Michael Felsberg
We present a novel variational approach to a tensor-based total variation formulation which is called gradient energy total variation, GETV. We introduce the gradient energy tensor…
Mapping-Based Image Diffusion
Freddie Åström, Michael Felsberg, George Baravdish
In this work, we introduce a novel tensor-based functional for targeted image enhancement and denoising. Via explicit regularization, our formulation incorporates application depen…
On the Choice of Tensor Estimation for Corner Detection, Optical Flow and Denoising
Freddie Åström, Michael Felsberg
Many image processing methods such as corner detection, optical flow and iterative enhancement make use of image tensors. Generally, these tensors are estimated using the structure…
On Tensor-Based PDEs and their Corresponding Variational Formulations with Application to Color Image Denoising
Freddie Åström, George Baravdish, Michael Felsberg
The case when a partial differential equation (PDE) can be considered as an Euler-Lagrange (E-L) equation of an energy functional, consisting of a data term and a smoothness term i…
Targeted Iterative Filtering
Freddie Åström, Michael Felsberg, George Baravdish +1
The assessment of image denoising results depends on the respective application area, i.e. image compression, still-image acquisition, and medical images require entirely different…
Predicting Signed Distance Functions for Visual Instance Segmentation
Emil Brissman, Joakim Johnander, Michael Felsberg
Visual instance segmentation is a challenging problem and becomes even more difficult if objects of interest varies unconstrained in shape. Some objects are well described by a rec…
Fast Iterative Five point Relative Pose Estimation
Johan Hedborg, Michael Felsberg
Robust estimation of the relative pose between two cameras is a fundamental part of Structure and Motion methods. For calibrated cameras, the five point method together with a robu…
Online Learning of Correspondences between Images
Michael Felsberg, Fredrik Larsson, Johan Wiklund +2
We propose a novel method for iterative learning of point correspondences between image sequences. Points moving on surfaces in 3D space are projected into two images. Given a poin…
Distractor-Aware Video Object Segmentation
Andreas Robinson, Abdelrahman Eldesokey, Michael Felsberg
Semi-supervised video object segmentation is a challenging task that aims to segment a target throughout a video sequence given an initial mask at the first frame. Discriminative a…
Composed Video Retrieval via Enriched Context and Discriminative Embeddings
Omkar Thawakar, Muzammal Naseer, Rao Muhammad Anwer +4
Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophist…
PALO: A Polyglot Large Multimodal Model for 5B People
Muhammad Maaz, Hanoona Rasheed, Abdelrahman Shaker +6
In pursuit of more inclusive Vision-Language Models (VLMs), this study introduces a Large Multilingual Multimodal Model called PALO. PALO offers visual reasoning capabilities in 10…
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT
Omkar Thawakar, Ashmal Vayani, Salman Khan +6
"Bigger the better" has been the predominant trend in recent Large Language Models (LLMs) development. However, LLMs do not suit well for scenarios that require on-device processin…
Leveraging the Power of Data Augmentation for Transformer-based Tracking
Jie Zhao, Johan Edstedt, Michael Felsberg +2
Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance. Previous works focus…
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching
Johan Edstedt, Georg Bökman, Mårten Wadenbäck +1
Keypoint detection is a pivotal step in 3D reconstruction, whereby sets of (up to) K points are detected in each view of a scene. Crucially, the detected points need to be consiste…
Learning to Augment: Hallucinating Data for Domain Generalized Segmentation
Qiyu Sun, Pavlo Melnyk, Michael Felsberg +1
Domain generalized semantic segmentation (DGSS) is an essential but highly challenging task, in which the model is trained only on source data and any target data is not available.…
Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning
Arvi Jonnarth, Jie Zhao, Michael Felsberg
Coverage path planning (CPP) is the problem of finding a path that covers the entire free space of a confined area, with applications ranging from robotic lawn mowing to search-and…
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
Emanuel Sanchez Aimar, Nathaniel Helgesen, Yonghao Xu +2
Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers. Thi…
GMSF: Global Matching Scene Flow
Yushan Zhang, Johan Edstedt, Bastian Wandt +3
We tackle the task of scene flow estimation from point clouds. Given a source and a target point cloud, the objective is to estimate a translation from each point in the source poi…
O Learning Deep O()-Equivariant Hyperspheres
Pavlo Melnyk, Michael Felsberg, Mårten Wadenbäck +2
In this paper, we utilize hyperspheres and regular -simplexes and propose an approach to learning deep features equivariant under the transformations of D reflections and rot…
RoMa: Robust Dense Feature Matching
Johan Edstedt, Qiyu Sun, Georg Bökman +2
Feature matching is an important computer vision task that involves estimating correspondences between two images of a 3D scene, and dense methods estimate all such correspondences…
High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation
Arvi Jonnarth, Yushan Zhang, Michael Felsberg
Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach invol…
Raw or Cooked? Object Detection on RAW Images
William Ljungbergh, Joakim Johnander, Christoffer Petersson +1
Images fed to a deep neural network have in general undergone several handcrafted image signal processing (ISP) operations, all of which have been optimized to produce visually ple…