Simon Weber
@SimWeberTUM
computer vision | phd candidate at @TU_Muenchen, visiting at @imperialcollege also on BlueSky: @simwebertum.bsky.social
Looking forward to presenting our paper "Finsler multi-dimensional scaling" at #CVPR2025 on Sunday 10:30am, Poster 462! We investigate a largely uncharted research direction in computer vision, aka Finsler manifolds...
Excited to be attending CVPR 2025 this week in Nashville! I’ll be presenting our recent work: “4Deform: Neural Surface Deformation for Robust Shape Interpolation” 📍 Poster session: [13th June 4pm-6pm poster #111] #CVPR2025 #computervision
We are thrilled that our group has twelve papers accepted at #CVPR2025! 🚀 Congratulations to all of our students for this great achievement! 🎉 For more details, check out: cvg.cit.tum.de
We are presenting DiffCD tomorrow morning at #ECCV2024! Come by poster 214 to discuss how to fit neural SDFs to point clouds, from a geometric perspective
Very excited to announce our paper: "DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting" at #ECCV2024! Paper: arxiv.org/abs/2407.17058 Code/project: github.com/linusnie/diffcd
Looking forward to present "PoVar" at #ECCV2024 tomorrow at 4:30pm, Poster 097 ! Check out our paper 📝 : arxiv.org/abs/2405.05079 our code 💻 : github.com/tum-vision/pov… and our video 📹: youtube.com/watch?v=PlFrfT…
Very glad to announce that our paper "Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment" has been accepted at #ECCV2024! Check out arxiv.org/abs/2405.05079
Feel free to drop by our poster stand tomorrow afternoon (Thursday 13:30-15:00, hall c 4-9, poster number #1402): icml.cc/virtual/2024/p… 😁
🤔 Variational learning is often thought to be impractical 🔥 Plot twist: it actually works better than Adam! Meet IVON, a new optimizer that brings the best out of variational learning – 🧵 (1/9) #NLProc #ICML2024 📰 arxiv.org/abs/2402.17641 youtu.be/TRNYnRRJBRg
🎷🎷Come and check out our paper on "Finsler-Laplace-Beltrami Operators with Application to Shape Analysis". Today (Wed) 10:30am at @CVPR. This project is led by the great @SimWeberTUM & Tom Dagès, joint force by @tumcvg, @MunichCenterML and @TechnionLive !
Very glad to announce that my two #CVPR2024 papers are now on arXiv! Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincaré Ball arxiv.org/abs/2404.03778 Finsler-Laplace-Beltrami Operators with Application to Shape Analysis arxiv.org/abs/2404.03999
A little late to the party but: 🥳 We are very proud that the students of our lab, together with great collaborators, are going to present 12 amazing works at #CVPR2024! For more info, visit our website: cvg.cit.tum.de
A little late to the party but: 🥳 We are very proud that the students of our lab, together with great collaborators, are going to present 12 amazing works at #CVPR2024! For more info, visit our website: cvg.cit.tum.de
@GaoMaolin and I will present this on Wednesday in the morning poster session. Come and talk to us!
ΣIGMA leverages the synergy between shape reconstruction and matching for sparse correspondence estimation of highly non-rigid shapes. ✅ initialization free ✅ provably invariant to rigid transformations/global scaling ✅ projected Laplace-Beltrami for shape reconstruction 3/n
Just read this cool 3D reconstruction paper on “Power BA” from @SimWeberTUM et al, one of the papers at CVPR this week (which I will unfortunately miss!).
Very glad to announce that our paper "Power Bundle Adjustment for Large-Scale 3D Reconstruction" has been accepted at #CVPR2023! Paper: arxiv.org/abs/2204.12834 Code: To be released in May Coauthors: Nikolaus Demmel, Tin Chon Chan, Daniel Cremers
The implementation of our #CVPR2023 paper "Power Bundle Adjustment for Large-Scale 3D Reconstruction" is now available. Project page: github.com/simonwebertum/… Implementation: github.com/NikolausDemmel…
Very glad to announce that our paper "Power Bundle Adjustment for Large-Scale 3D Reconstruction" has been accepted at #CVPR2023! Paper: arxiv.org/abs/2204.12834 Code: To be released in May Coauthors: Nikolaus Demmel, Tin Chon Chan, Daniel Cremers