Univ.Ass. Dipl.-Ing.
  • Scientist







perler [at]


  • PhD student


  • I'm in room HF 05 17. It's at Favoritenstrasse 9-11 / E193-02, Stiege 2, 5th floor, follow the hallway right. It's after the glass door to Stiege 3. Go through the office HF 05 13 of Hiro and Christian.
  • I can speak with you in English and German and I can try to speak French.
  • Are you unsure how you should address me in an e-mail? Just write "Hi Philipp" or similar.

Research Work

  • Surface reconstruction from point clouds
  • Geometry processing
  • Deep learning

Additional interests:

  • Virtual Reality
  • Physical Simulations
  • Fabrication
  • Natural Language Processing


Thesis Supervision

See other programs, games and work on my private website.

Short Bio

Surface reconstruction from point clouds

Research Projects

Courses in the current semester


5 Publications found:
Image Bib Reference Publication Type
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
Front side of the card as an image Martin Ilčík, Philipp ErlerORCID iD
X-Mas Card 2021
[Card] [Music]
X-Mas Card
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 Ohrhallinger, 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
Philipp ErlerORCID iD
Haptic Feedback in Room-Scale VR
[thesis] [VR Apps Repo] [Analyzer Repo]
Master Thesis
Philipp ErlerORCID iD
Finite Element Fluids in Matlab
Student Project
Download list as Bibtex, HTML (Advanced, Expert), JSON (with referenced objects), CSV, Permalink