The core idea in this project is to capture the shape of physical objects in real time, with guaranteed precision, and to reconstruct the shape boundaries with minimal geometry. An example application is to let untrained users acquire shapes using emerging mobile sensing devices such as Google’s Project Tango. The user moves the sensor around the object, guided by immediate visual feedback on the input sampling quality. The output is a topologically clean mesh consisting of just the vertices required to represent its features to the desired approximation. The real-time reconstruction enables numerous geometry-processing applications to be taken online, such as shape retrieval/matching, harvesting real-world geometry into a cloud, perspective photo correction, interactive modeling, augmented reality, physics simulation, or fabrication.

Funding

  • FWF P24600-N23

Team

Research Areas

  • Geometry Processing
    Uses concepts from applied mathematics and computer science to design efficient algorithms for the reconstruction, analysis, manipulation, simulation and transmission of complex 3D models. Example applications are collision detection, reconstruction, compression, occlusion-aware surface handling and improved sampling conditions.

Publications

13 Publications found:
Image Bib Reference Publication Type
2024
PPSurf teaser with comparison Philipp ErlerORCID iD, Lizeth Fuentes-PerezORCID iD, Pedro Hermosilla-CasajusORCID iD, Paul Guerrero, Renato Pajarola, Michael WimmerORCID iD
PPSurf: Combining Patches and Point Convolutions for Detailed Surface Reconstruction
Computer Graphics Forum, 43(1):tbd-tbd, January 2024. [paper] [teaser] [Live System] [Repo (Github)]		 Journal Paper with Conference Talk
2021
Mohamed Radwan, Stefan OhrhallingerORCID iD, Michael WimmerORCID iD
Fast occlusion-based point cloud exploration
The Visual Computer Journal, 37:2769-2781, September 2021. [paper] 		Journal Paper with Conference Talk
2020
We present Points2Surf, a method to reconstruct an accurate implicit surface from a noisy point cloud. Unlike current data-driven surface reconstruction methods like DeepSDF and AtlasNet, it is patch-based, improves detail reconstruction, and unlike Screened Poisson Reconstruction (SPR), a learned prior of low-level patch shapes improves reconstruction accuracy. Note the quality of reconstructions, both geometric and topological, against the original surfaces. The ability of Points2Surf to generalize to new shapes makes it the first learning-based approach with significant generalization ability under both geometric and topological variations. Philipp ErlerORCID iD, Paul Guerrero, Stefan OhrhallingerORCID iD, Michael WimmerORCID iD, Niloy Mitra
Points2Surf: Learning Implicit Surfaces from Point Clouds
In Computer Vision -- ECCV 2020, pages 108-124. October 2020.
[points2surf_paper] [short video] 		Conference Paper
2019
Horst Gruber
Extensible Image Classification
 Bachelor Thesis
Manifold curve fitted samples with highly varying noise Stefan OhrhallingerORCID iD, Michael WimmerORCID iD
FitConnect: Connecting Noisy 2D Samples by Fitted Neighborhoods
Computer Graphics Forum, 38(1):126-137, February 2019. [paper] [Replicability Source Code]		 Journal Paper with Conference Talk
2018
Stefan OhrhallingerORCID iD, Michael WimmerORCID iD
StretchDenoise: Parametric Curve Reconstruction with Guarantees by Separating Connectivity from Residual Uncertainty of Samples
In Proceedings of Pacific Graphics 2018, pages 1-4. August 2018.
[image] [paper] [Extended version] [source]		 Conference Paper
2017
Image vs. depth image Michael Pointner
Multi-Focal Image Generation using Automatic Depth-Based Focus Selection
[image] [thesis] 		Bachelor Thesis
Kinect v2 and Phab2Pro noise model evaluation Nicolas Grossmann
Extracting Sensor Specific Noise Models
[thesis] 		Bachelor Thesis
Camera calibration prior to extraction of depth values Thomas Köppel
Extracting Noise Models – considering X / Y and Z Noise
[thesis] 		Bachelor Thesis
Occlusion-aware generation of a cutaway illustration. Mohamed Radwan, Stefan OhrhallingerORCID iD, Elmar Eisemann, Michael WimmerORCID iD
Cut and Paint: Occlusion-Aware Subset Selection for Surface Processing
In Proceedings of Graphics Interface 2017, pages 82-89. May 2017.
[paper] 		Conference Paper
Siegfried Reinwald
Fast kNN in Screen Space on GPU
[image] [thesis] 		Bachelor Thesis
2016
null Jeremy Forsythe, Vitaliy Kurlin, Andrew Fitzgibbon
Resolution-independent superpixels based on convex constrained meshes without small angles
Lecture Notes in Computer Science (LNCS), 10072:223-233, December 2016. [paper] [slides] 		Journal Paper with Conference Talk
Stefan OhrhallingerORCID iD, Scott A. Mitchell, Michael WimmerORCID iD
Curve Reconstruction with Many Fewer Samples
Computer Graphics Forum, 35(5):167-176, 2016. [paper] [slides] [Reproducibility Source Code]		 Journal Paper with Conference Talk
Download list as Bibtex, HTML (Advanced, Expert), JSON (with referenced objects), CSV, Permalink

Details

Workgroups
Rendering and Modeling
Project Leader
Michael Wimmer

Start Date

End Date

Hot Links

Project page in TISS Research Portal