ドイツ人のフラットメイトに納豆あげたら、怯えてたけど結構美味しかったみたい。予想してた反応と違かった😂

勝った！！！！！！

決勝すごかったわ！！

機械学習コンペ出て7位だった😢でも久しぶりで楽しかった！

／ 2023 J1リーグ 初ゴールは西村拓真🔥 ＼ #西村拓真 選手が 落ち着いてコースを狙いゴール✨ #fmarinos｜#Jリーグ

日本に帰って、やよい軒と、びっくりドンキーと、ねぎしに行きたい

林選手と奥抜選手の2人加入したから、FCニュルンベルク観てきた。退場者3人出る試合で荒れてたけど、逆転勝ちしてめっちゃ面白かったわ！

今年はバイエルン州の大学が参加して、2位でした🙂

Matérn Kernels for Tunable Implicit Surface Reconstruction Paper: arxiv.org/abs/2409.15466 We use Matérn kernels for 3D surface reconstruction, acting as a drop-in replacement of the arc-cosine kernel in frameworks such as Neural Splines & Neural Kernel Fields. Code on GitHub!

I'm looking forward to presenting RANRAC: Robust Neural Scene Representations via Random Ray Consensus European Conference on Computer Vision #ECCV2026 next week. In a coop of TU Delft & FAU Erlangen-Nbg we pushed RANSAC's limits enabling robust neural fields: graphics.tudelft.nl/RANRAC Bernhard Egger Elmar Eisemann Andreea Ardelean

Today Takuma Nishimura takuma is presenting ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting at the AI for visual arts workshop @AI4VAECCV24 #ECCV2024 joint work with Andreea Ardelean and Martin Oeggerli (artist) ronly2460.github.io/ArCSEM/

I am happy to announce that our work “ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimation” has been accepted to ISMAR 2024 in Seattle. Project Page: hex-lab.io/asdf/

Want to do 2 years of postdoc Cognitive Computer Vision Lab FAU Erlangen-Nbg in Germany with me? Open Topic around 3D Computer Vision, Neural Rendering, Human Vision, Inverse Rendering, Statistical Shape Modelling or related See the following tweets to see our featured research:

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. (1/n)

応募しても無視され、内気すぎてロビーで誰にも話しかけられなかった青年 27年後、資産27兆円の経営者に ネットスケープ社が見逃した天才がいた... つづく↓

Happy to share our latest 3D generative breast model: the *implicit* RBSM, or iRBSM for short. As opposed to its PCA-based predecessor, the iRBSM leverages implicit neural representations, yielding a highly detailed and expressive 3D breast model. Paper: arxiv.org/abs/2412.13244