Sebastian Hartwig retweeted
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: huggingface.co/papers/2411.1…
🤗 Space: huggingface.co/spaces/leonsi…
1/5
Sebastian Hartwig retweeted
🚨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: huggingface.co/papers/2411.1…
🤗 Space: huggingface.co/spaces/leonsi…
1/5
Check out this work during today's poster session at #CVPR2024
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: leonsick.github.io/depthg
Sebastian Hartwig retweeted
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: leonsick.github.io/depthg – at Seattle, WA
Sebastian Hartwig retweeted
Great work and charming presenter confirmed ;) come check it out!
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: leonsick.github.io/depthg
Sebastian Hartwig retweeted
endoftext is live on @ProductHunt
@a_a_cabrera and I have been building for the past ~2 months and would love to read your comments.
producthunt.com/posts/endoft…
We are happy to announce our survey and taxonomy on text to image synthesis evaluation!
There are interesting differences between SOTA metrics and their capabilities of measuring text-conditioned image quality.
Check it out at: huggingface.co/papers/2403.1…
I developed a small python wrapper of civitai.com REST API available at: github.com/kopetri/civitai
Sebastian Hartwig retweeted
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:
hub.zenoml.com/report/a13x/W…
According to the giants of visual computing the alignment to human preference is still an open challenge.
We just posted a report on the state of the art in diffusion models for visual computing: arxiv.org/abs/2310.07204
If you're new to diffusion models, or maybe just want a recap of everything that's been going on lately---this is a great place to start.
Sebastian Hartwig retweeted
Happy to share our new pre-print on guiding unsupervised semantic segmentation with depth maps!📄👀
TLDR; We guide the feature space for unsupervised segmentation with information from the 3D space through depth-feature correlation.
HF Paper Page: huggingface.co/papers/2309.1…
More 👇
Sebastian Hartwig retweeted
📜 Explore your large image datasets using their semantic content.
✍️ @a13xba, C. van Onzenoodt, @ResearchDaniel, and T. Ropinski
👉 Demo: tinyurl.com/3f2hnv3c
#Shortpaper #EuroVis #Eurovis2023
Sebastian Hartwig retweeted
Amazing keynote by @GordonWetzstein at #Eurographics!
Talking about 3d generative methods, diffusion models, and neural scene representations, and much more!
Check out his take on open problems - it's a fantastic research area :)
Sebastian Hartwig retweeted
I am happy to announce that I have joined the Computer Vision Lab at TU Wien as Assistant Professor of AI for Visual Computing.
If you are looking to do your PhD in 3D Vision in the best-ranked city worldwide, in the next months I will have an open position. Stay tuned!
Sebastian Hartwig retweeted
Great overview of the research challenges we have @sigmacomputing and in the broader cloud data analytics space.
Published a blog post expanding on the research challenges & opportunities around interactive cloud data analytics systems I presented earlier at the @UCBEPIC meeting. We're @sigmacomputing excited to explore many of the ideas with the help of our users.
medium.com/@cagatay.demiralp…
Sebastian Hartwig retweeted
Handwriting training can benefit from #AR, as our paper "SpARklingPaper: Enhancing Common Pen- And Paper-Based Handwriting Training for Children by Digitally Augmenting Papers Using a Tablet Screen" shows. #IMWUT #UbiComp2022 (1/2)
Sebastian Hartwig retweeted
Replying to @a13xba
@a13xba introduces our paper on how to represent missing data in parallel coordinates @EuroVisConf @mi_uulm
diglib.eg.org/handle/10.1111…
Sebastian Hartwig retweeted
The last version of our pre-print: "Contrastive Representation Learning for 3D Protein Structures" is now in arxiv: arxiv.org/abs/2205.15675

























