Pedro Hermosilla
@Pedro_He_Ca
Followers
253
Following
392
Media
13
Statuses
74
Assistant Professor at @tu_wien in AI for Visual Computing
Vienna, Austria
Joined February 2012
Happy to share our new #SIGGRAPHAsia2025 paper! If you are tired of using marching cubes to extract your mesh from neural implicit representations, check out Marching Neurons! Project: https://t.co/nGpWOEl06h Arxiv: https://t.co/FHYJzwAR7y
0
8
39
Happy to share our recent work on hierarchical 3D scene understanding using hyperbolic spaces, which has recently been accepted to #NeurIPS2025 !!!🥳
🚀 OpenHype goes #NeurIPS2025! Over the moon to share that our paper was accepted! 🎉 👥With: @sebastiankoch98, @Poiex, Timo Ropinski and @Pedro_He_Ca 👉Project page:
0
0
5
Finally sharing: our code for the paper on *efficient SE(3) convolutions for point clouds*, presented at 3DV’25, is online! If you’re interested, check it out and let me know what you think 🙌 💻👉 https://t.co/8UgV36PSx1 💡Project Page: https://t.co/FZMFKccG9Y
@Pedro_He_Ca
0
1
4
Happy to congratulate @weijler_lisa on her best poster award at #ICVSS2025! A well-deserved recognition to an amazing PhD so far!
Had the best time at #ICVSS2025! Learned so much from brilliant minds in (3D) CV & AI - and winning a Best Presentation Award was the cherry on top 🍒🎉 Grateful for the chance to connect, learn, and grow with such an inspiring and driven community!
0
0
5
Accepted at #ICCV2025! 🎉 Many thanks to my amazing co-authors @xeTaiz, @Kopetri, @Pedro_He_Ca & Timo. Looking forward to the conference in Hawaii!🌺
🚨Super exited to share our new work CutS3D for unsupervised instance segmentation! 👀TLDR We connect semantics and 3D to cut instances and train a detector with spatial confidence. 🤗 Paper Page: https://t.co/d64oM1gaYj 🤗 Space: https://t.co/Ug7qacOBiZ 1/5
0
3
10
Are you tired of projecting 2D features into 3D for general problem solving? Try our self-supervised model, which generates semantic off-the-shelf features natively in 3D! #CVPR2025 Project: https://t.co/jI8ZcpuXqY Arxiv: https://t.co/HyjkrCpjSO Github: https://t.co/d1qh5GLsa8
0
4
8
🎉 Excited to share RelationField: Relate Anything in Radiance Fields, accepted at #CVPR2025 The first method to extract inter-object relationships directly in radiance fields. 📝Paper https://t.co/Rr1tCr1vGc 🚀Project https://t.co/JWIq7fCf68 👨💻Code https://t.co/bGdnUqcewq
2
5
15
🚨Super exited to share our new work CutS3D for unsupervised instance segmentation! 👀TLDR We connect semantics and 3D to cut instances and train a detector with spatial confidence. 🤗 Paper Page: https://t.co/d64oM1gaYj 🤗 Space: https://t.co/Ug7qacOBiZ 1/5
1
10
35
I will be at #CVPR2024 next week, presenting Open3DSG (Open-Vocabulary 3D Scene Graph Prediction) on Thursday morning. 📝Paper https://t.co/hQB3YnTSLZ 👨💻Code https://t.co/AhQSGVHLiW 🚀Project https://t.co/oWSwr0awRK
1
2
6
Can't wait to present our research on depth-guided unsupervised segmentation at #CVPR2024 tomorrow! 🙌 Make sure to stop by our poster #336 tomorrow during the Wednesday AM poster session 👀 For more, check out our project page: https://t.co/MsqEgattDr
1
3
9
If you have missed my poster presentation at #3DV2024, feel free to check it out here. I will be at 3DV until Thursday. If you see me don't hesitate to approach me.
0
1
6
I am excited to announce that #Open3DSG was accepted at #CVPR2024🥳 In this paper, we introduce open-vocabulary 3D Scene Graphs. We go beyond existing methods that only consider OV objects and focus particularly on open-vocabulary relationships. 📚abs: https://t.co/hQB3YnTkWr
2
2
16
🎉 Exciting news! Our research on weakly supervised capsid detection in electron microscopy images has been accepted at #ICLR2024! 🥳 🔍 TLDR; We're introducing an optimization approach with shrinking receptive field to enhance virus particle detection. More details soon!
0
4
6
How similar are 3D scene graphs and language? In our #3DV2024 work Lang3DSG, we find many synergies enabling improved scene graph learning and scene graph-guided zero-shot downstream applications. For more information check out: https://t.co/yLqow4m2jo
2
2
7
I am excited to be featured in the #WACV2024 newsletter part of the @RSIPvision magazine, with my conference work SGRec3D. Check it out here for more: https://t.co/NBWQe0k12r
0
3
11
🥳 Our paper "SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction" was accepted at #WACV2024 📕 arXiv: https://t.co/BEbPEIA8vQ 🖥️project page:
arxiv.org
In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships. However,...
🚀 Exciting news: "SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction" is now available at https://t.co/BEbPEIA8vQ Collaboration between @Bosch_AI and @uni_ulm
@Pedro_He_Ca, Narunas Vaskevicius, Mirco Colosi, Timo Ropinski (1/8) A thread 🧵
0
2
7
𝗗𝗼𝗻’𝘁 𝗯𝗹𝗶𝗻𝗱𝗹𝘆 𝘁𝗿𝘂𝘀𝘁 𝘁𝗵𝗲 𝗢𝗽𝗲𝗻 𝗟𝗟𝗠 𝗟𝗲𝗮𝗱𝗲𝗿𝗯𝗼𝗮𝗿𝗱! We used @try_zeno to explore the Open LLM Leaderboard data. Spoiler: Unless you use LLMs for multiple choice questions, these benchmarks aren’t that helpful. Zeno Report: https://t.co/9uucMB3GEK
4
18
81
Fun fact: One of our co-authors has won the Nobel Prize in chemistry! 🙌🙌 #femtophotography @GILabUZ @medialab
3
17
138
ENTREVISTA | Belén Masiá @ARandomRedCat: "La curiosidad es imprescindible si quieres trabajar en investigación", por @MbsComunicacion
https://t.co/fXSZkNrRXk via @eldiarioaragon
eldiario.es
Belen Masiá es Doctora en Ingeniería Informática y forma parte del grupo de investigación Graphics and Imaging Lab del Instituto de Investigación en Ingeniería de Aragón de la Universidad de Zaragoza
0
5
18
🚀 Exciting news: "SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction" is now available at https://t.co/BEbPEIA8vQ Collaboration between @Bosch_AI and @uni_ulm
@Pedro_He_Ca, Narunas Vaskevicius, Mirco Colosi, Timo Ropinski (1/8) A thread 🧵
1
4
8