Maximilian Weiherer
@maxweiherer.bsky.social
PhD student at @fau.de. Part of @cogcovi.bsky.social. I’m working at the intersection of computer vision, computer graphics, and machine learning. I like kernels.
mweiherer.github.io
mweiherer.github.io
Absolut. Und dann auch noch j = sqrt(-1).
February 20, 2025 at 6:24 PM
Absolut. Und dann auch noch j = sqrt(-1).
Jetzt weißt du wieso ich mich angegriffen fühle wenn mich jemand als Ingenieur bezeichnet. Ich möchte freundlich darauf hinweisen dass nicht alle Ingenieure pi auf 3 abrunden, oder e auf 2.
February 20, 2025 at 5:36 PM
Jetzt weißt du wieso ich mich angegriffen fühle wenn mich jemand als Ingenieur bezeichnet. Ich möchte freundlich darauf hinweisen dass nicht alle Ingenieure pi auf 3 abrunden, oder e auf 2.
(5/5) Huge thanks to my co-authors, Antonia von Riedheim, Vanessa Brébant, @visionbernie.bsky.social, and Christoph Palm.
December 19, 2024 at 11:23 AM
(5/5) Huge thanks to my co-authors, Antonia von Riedheim, Vanessa Brébant, @visionbernie.bsky.social, and Christoph Palm.
(4/5) The resulting model is free of correspondence errors, captures detailed surface geometry, and outperforms the RBSM in various surface reconstruction tasks.
The iRBSM is publicly available for research purposes!
Model: rbsm.re-mic.de/implicit
Code: github.com/mweiherer/ir...
The iRBSM is publicly available for research purposes!
Model: rbsm.re-mic.de/implicit
Code: github.com/mweiherer/ir...
December 19, 2024 at 11:23 AM
(4/5) The resulting model is free of correspondence errors, captures detailed surface geometry, and outperforms the RBSM in various surface reconstruction tasks.
The iRBSM is publicly available for research purposes!
Model: rbsm.re-mic.de/implicit
Code: github.com/mweiherer/ir...
The iRBSM is publicly available for research purposes!
Model: rbsm.re-mic.de/implicit
Code: github.com/mweiherer/ir...
(3/5) Using an implicit (correspondence-free) representation to model breast shapes from surface-only 3D scans is highly advantageous, as registering these scans is extremely hard: almost no features, large deformations, and severe occlusions (esp. underbust).
December 19, 2024 at 11:23 AM
(3/5) Using an implicit (correspondence-free) representation to model breast shapes from surface-only 3D scans is highly advantageous, as registering these scans is extremely hard: almost no features, large deformations, and severe occlusions (esp. underbust).
(2/5) Our model uses a DeepSDF architecture and is trained directly on 168 raw 3D breast scans--without ground truth supervision. Contrary to the RBSM, no surface registration is required to bring training data into correspondence.
December 19, 2024 at 11:23 AM
(2/5) Our model uses a DeepSDF architecture and is trained directly on 168 raw 3D breast scans--without ground truth supervision. Contrary to the RBSM, no surface registration is required to bring training data into correspondence.