activity
20202026
collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2026

BlobBoards: Robust Markers for Accurate Pose

James Pritts, Till Sittart, Hendrik Sauer +4

We propose BlobBoards, a fiducial marker system comprising a dense, multi-scale field of Gaussian blobs and a feature-based pipeline for joint detection, identification, and pose e…

cs.CV2026

BALTIC: A Benchmark and Cross-Domain Strategy for 3D Reconstruction Across Air and Underwater Domains Under Varying Illumination

Michele Grimaldi, David Nakath, Oscar Pizarro +3

Robust 3D reconstruction across varying environmental conditions remains a critical challenge for robotic perception, particularly when transitioning between air and water. To addr…

cs.CV2025

Optical Ocean Recipes: Creating Realistic Datasets to Facilitate Underwater Vision Research

Patricia Schöntag, David Nakath, Judith Fischer +2

The development and evaluation of machine vision in underwater environments remains challenging, often relying on trial-and-error-based testing tailored to specific applications. T…

cs.CV2025

Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes

Mengkun She, Felix Seegräber, David Nakath +2

We address the challenge of constructing a consistent and photorealistic Neural Radiance Field in inhomogeneously illuminated, scattering environments with unknown, co-moving light…

cs.CV2024

Refractive COLMAP: Refractive Structure-from-Motion Revisited

Mengkun She, Felix Seegräber, David Nakath +1

In this paper, we present a complete refractive Structure-from-Motion (RSfM) framework for underwater 3D reconstruction using refractive camera setups (for both, flat- and dome-por…

cs.CV2023

Visual Tomography: Physically Faithful Volumetric Models of Partially Translucent Objects

David Nakath, Xiangyu Weng, Mengkun She +1

When created faithfully from real-world data, Digital 3D representations of objects can be useful for human or computer-assisted analysis. Such models can also serve for generating…