Second day at #automatica showcasing our KARVIMIO project

First day of #IEEEVR 2025. starting early in the morning with the 3rd Workshop on XR Technologies for Healthcare, Wellbeing, and Medicine 2025. Presenting our review paper with a quick lighting talk and two poster session. #VR #workshop #conference

Congrats to Daniela et al.! Super happy that one of my drawings made it to the title page of the journal! And even more happy for Daniela and here co authors on their new research :) #FAU #drawing

Ours (#SCGS):

Gaga rendering, but it seems that the segmentation is really difficult to keep consistent:

Currently running #Gaga on our new dataset (hannahhaensen.github.io) after testing SAM-Tracking and DPT-Seg for our main paper, I now tested entityseg used in #Gaga. Consistency in outdoor scenes seems to be quite a challenge: Frame 15 and 16 in our dataset on the Lake scene using entity_seg (1/n)

The reflections in the water could be a super cool challenge for you. If you want to be on the leader board just drop me an email with your SSIM and PSNR results and a link to your paper or project page. (2/n)

We have a pretty cool and new dataset for novel view synthesis. #GaussianSplatting #NeRF.

It is available at OSF and focuses on outdoor scenes. If you are doing semantic Gaussian Splatting or general Gaussian Splatting check it out (1/n).

hannahhaensen.github.io/SCGS/

I am very excited to announce our paper “DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields” has been accepted to #IEEE RA-L.

Paper: ieeexplore.ieee.org/document/107...
Project page: hannahhaensen.github.io/DynaMoN/
Code: github.com/HannahHaense...

In case you wonder what our SIGBOVIK paper was about.

Thanks to @visionbernie.bsky.social my first printed conference proceedings will make it into my bookshelf! Shoutout also to all #SIGBOVIK co-authors @maxweiherer.bsky.social @kapoorshreya18.bsky.social @andreead-a.bsky.social

Best conference at the best date 🙂‍↕️

Comparison on our new dataset #nerf #computervision #neuralrendering

🚨 Paper Alert 🚨 #CVIU
NeRFtrinsic Four: An End-To-End Trainable NeRF Jointly Optimizing Diverse Intrinsic and Extrinsic Camera Parameters has been accepted to #CVIU!!!
Many thanks to my co-authors! Shout out to Fabian Deuser, @visionbernie.bsky.social,Norbert Oswald and Daniel Roth.
(1/4)

Interested in multi-part 3D object tracking? "GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidance", authored by
Shiyu, myself, Niklas, @visionbernie.bsky.social , Julian, and, Daniel. GBOT is presented @IEEEVR in Mondays session USA, Fantasia Ballroom G UTC-4

I am very excited to announce that our review, “Indoor Synthetic Data Generation: A Systematic Review”, got accepted at Computer Vision and Image Understanding (CVIU). Our work is now available.

hannahhaensen.github.io/Synthetic-Da...

Being at IEEE AIxVR was a pleasure.

More information about our paper "MR-Sense: A Mixed Reality Environment Search Assistant for Blind and Visually Impaired People" can be found at hannahhaensen.github.io/mr-sense/

Many thanks to my co-authors and to the participants of the user study.
#aixvr