Search Results for author: Vitjan Zavrtanik

Found 7 papers, 6 papers with code

TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection

no code implementations • 16 Nov 2023 • Matic Fučka, Vitjan Zavrtanik, Danijel Skočaj

We propose a novel transparency-based diffusion process, where the transparency of anomalous regions is progressively increased, restoring their normal appearance accurately and maintaining the appearance of anomaly-free regions without loss of detail.

Ranked #8 on Anomaly Detection on VisA

Anomaly Detection

Paper
Add Code

Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation

1 code implementation • 2 Nov 2023 • Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj

(ii) We tackle the lack of diverse industrial depth datasets by introducing a simulation process for learning informative depth features in the depth encoder.

Ranked #1 on RGB+3D Anomaly Detection and Segmentation on MVTEC 3D-AD

Depth Anomaly Detection and Segmentation RGB+3D Anomaly Detection and Segmentation

Paper
Code

A Low-Shot Object Counting Network With Iterative Prototype Adaptation

1 code implementation • ICCV 2023 • Nikola Djukic, Alan Lukezic, Vitjan Zavrtanik, Matej Kristan

The standard few-shot pipeline follows extraction of appearance queries from exemplars and matching them with image features to infer the object counts.

Ranked #1 on Object Counting on FSC147

Object Object Counting +1

Paper
Code

DSR -- A dual subspace re-projection network for surface anomaly detection

1 code implementation • 2 Aug 2022 • Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj

The state-of-the-art in discriminative unsupervised surface anomaly detection relies on external datasets for synthesizing anomaly-augmented training images.

Ranked #1 on Supervised Defect Detection on KolektorSDD2