From the 1 of 3 linked papers with an AI index.
3 papers
Do Image Editing Models Understand Lighting?
Tim Küchler, Johann-Friedrich Feiden, Matthias NieÃner +1
The paper introduces a new real‑world HDR benchmark (3DLP) that measures how well generative image‑editing models can edit lighting by turning light probes on and off, and evaluate…
A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation
Denis Zavadski, Damjan Kalšan, Tim Küchler +3
Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly…
Online Video Depth Anything: Temporally-Consistent Depth Prediction with Low Memory Consumption
Johann-Friedrich Feiden, Tim Küchler, Denis Zavadski +2
Depth estimation from monocular video has become a key component of many real-world computer vision systems. Recently, Video Depth Anything (VDA) has demonstrated strong performanc…