Recherche

Afficher tous les résultats pour

Accueil

Personne

Radhakrishna Achanta

À propos
Confidentialité
Mentions légales

Graph Chatbot

Publications associées (36)

Page 2 sur 2

Exploiting the Signal-Leak Bias in Diffusion Models

Athanasios Fitsios, Sabine Süsstrunk, Radhakrishna Achanta, Mahmut Sami Arpa, Martin Nicolas Everaert

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate that this signa ...

2024

Single Image Reflection Suppression

Sabine Süsstrunk, Radhakrishna Achanta, Nikolaos Arvanitopoulos Darginis

Reflections are a common artifact in images taken through glass windows. Automatically removing the reflection artifacts after the picture is taken is an ill-posed problem. Attempts to solve this problem using optimization schemes therefore rely on various ...

Ieee2017

Scale-Adaptive Superpixels

Pascal Fua, Sabine Süsstrunk, Radhakrishna Achanta, Pablo Marquez Neila

Size uniformity is one of the prominent features of superpixels. However, size uniformity rarely conforms to the varying content of an image. The chosen size of the superpixels therefore represents a compromise - how to obtain the fewest superpixels withou ...

Society for Imaging Science and Technology2018

Towards real-time digital twins for post-earthquake damage assessment of masonry buildings

Katrin Beyer, Radhakrishna Achanta, Bryan German Pantoja Rosero

Currently, post-earthquake assessment is performed visually, which implies that inspectors visit the damaged buildings and, based on their expertise, assign a damage grade. Yet, visual inspection is subjective, time-consuming and difficult to document. In ...

2023

Face Recognition in Real-world Images

Xavier Philippe Marie Fontaine, Sabine Süsstrunk, Radhakrishna Achanta

Face recognition systems are designed to handle well-aligned images captured under controlled situations. However real-world images present varying orientations, expressions, and illumination conditions. Traditional face recognition algorithms perform poor ...

Ieee2017

Frequency-tuned Salient Region Detection

Sabine Süsstrunk, Radhakrishna Achanta

Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with ...

2009

Image Summaries using Database Saliency

Pascal Fua, Sabine Süsstrunk, Radhakrishna Achanta, Appu Shaji

It is useful to have a small set of representative images from a database of thousands of images to summarize its content. There are two key aspects of such image summaries: how to generate them and how to present them. We address both issues. We extend th ...

2009

GUI-Aided NIR and Color Image Blending

Sabine Süsstrunk, Radhakrishna Achanta

A near-infrared (NIR) image of a scene contains different information than the corresponding visible spectrum (RGB) image, due to physical phenomena related to scattering, absorption, and reflectance of the different radiation bands. It can be desirable to ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2010

Diffusion in Style

Sabine Süsstrunk, Radhakrishna Achanta, Mahmut Sami Arpa, Martin Nicolas Everaert

We present Diffusion in Style, a simple method to adapt Stable Diffusion to any desired style, using only a small set of target images. It is based on the key observation that the style of the images generated by Stable Diffusion is tied to the initial lat ...

2023

Extreme Image Completion

Sabine Süsstrunk, Radhakrishna Achanta, Nikolaos Arvanitopoulos Darginis

It is challenging to complete an image whose 99 percent pixels are randomly missing. We present a solution to this extreme image completion problem. As opposed to existing techniques, our solution has a computational complexity that is linear in the number ...

Ieee2017

Saliency Detection using Maximum Symmetric Surround

Sabine Süsstrunk, Radhakrishna Achanta

Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. Recently, full-resolution salient maps that retain well-defined boundaries have attracted attention. In these map ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2010

Superpixels and Polygons using Simple Non-Iterative Clustering

Sabine Süsstrunk, Radhakrishna Achanta

We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel bou ...

Ieee2017

Scale-adaptive media item segmentation technique

Radhakrishna Achanta

The present invention concerns a method of segmenting a media item comprising media elements. The method comprises: selecting a first seed media element for a first cluster of media elements, referred to hereinafter as a first adaptel; selecting a second s ...

2017

Digital Twins of Stone Masonry Buildings for Damage Assessment

Katrin Beyer, Radhakrishna Achanta, Bryan German Pantoja Rosero

Digital twins are virtual models of physical objects or systems that enable real-time monitoring and analysis. In the ﬁeld of stone masonry buildings, digital twins can be used to assess damage, predict maintenance needs, and opti- mize building performanc ...

Springer2024

Text Recognition in Natural Images Using Multiclass Hough Forests

Sabine Süsstrunk, Radhakrishna Achanta, Gökhan Yildirim

Text detection and recognition in natural images are popular yet unsolved problems in computer vision. In this paper, we propose a technique that attempts to detect and recognize text in a unified manner by searching for words directly without reducing the ...

2013

A Fully Automated Approach to Segmentation of Irregularly Shaped Cellular Structures in EM Images

Pascal Fua, Vincent Lepetit, Radhakrishna Achanta, Kevin Smith, Aurélien Lucchi

While there has been substantial progress in segmenting natural im-ages, state-of-the-art methods that perform well in such tasks unfortunately tend to underperform when confronted with the different challenges posed by electron microscope (EM) data. For e ...

Springer2010