Konrad Schindler

40

Papers

104

Total Citations

Papers (40)

StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation

CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion

Video Depth without Video Models

Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments

A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking

A Variational Perspective on Generative Protein Fitness Optimization

GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation

Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-Resolution Model for Multi-Class Volumetric Labeling

Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction

Cataloging Public Objects Using Aerial and Street-Level Images - Urban Trees

A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos

From Two Rolling Shutters to One Global Shutter

Predator: Registration of 3D Point Clouds With Low Overlap

Learning Graph Regularisation for Guided Super-Resolution

BARC: Learning To Regress 3D Dog Shape From Images by Exploiting Breed Information

Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries

BiasBed - Rigorous Texture Bias Evaluation

Guided Depth Super-Resolution by Deep Anisotropic Diffusion

BITE: Beyond Priors for Improved Three-D Dog Pose Estimation

Massively Parallel Multiview Stereopsis by Surface Normal Diffusion

Hyperpoints and Fine Vocabularies for Large-Scale Location Recognition

Hyperspectral Super-Resolution by Coupled Spectral Unmixing

Learned Multi-Patch Similarity

Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations

Semantically Informed Multiview Surface Refinement

Guided Super-Resolution As Pixel-to-Pixel Transformation

Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation

Neural LiDAR Fields for Novel View Synthesis

Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion

Dynamic 3D Scene Analysis by Point Cloud Accumulation

In the Light of Feature Distributions: Moment Matching for Neural Style Transfer

Box2Poly: Memory

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Dynamic LiDAR Re-simulation using Compositional Neural Fields

Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds

Joint Tracking and Segmentation of Multiple Targets

Large-Scale Location Recognition and the Geometric Burstiness Problem

Contour Detection in Unstructured 3D Point Clouds

FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation