Computer Vision and Machine Learning at MPI Informatics
@cvml.mpi-inf.mpg.de
Computer Vision and Machine Department at the Max Planck Institute for Informatics | https://www.mpi-inf.mpg.de/departments/computer-vision-and-machine-learning/
AIM Project Page: eyad-alshami.github.io/aim-page/
AIM: Amending Inherent Interpretability via Self-Supervised Masking
AIM: Amending Inherent Interpretability via Self-Supervised Masking
eyad-alshami.github.io
October 21, 2025 at 10:37 AM
AIM Project Page: eyad-alshami.github.io/aim-page/
Reposted by Computer Vision and Machine Learning at MPI Informatics
ICCV 2025 kicks off tomorrow! We look forward to welcoming everyone to Hawaii 🌺
October 19, 2025 at 3:50 AM
ICCV 2025 kicks off tomorrow! We look forward to welcoming everyone to Hawaii 🌺
October 19, 2025 at 7:49 AM
MVGBench: “A Comprehensive Benchmark for Multi-view Generation Models” — measures 3D consistency & image quality for fair comparisons.
By Xianghui Xie, Jan Eric Lenssen, Gerard Pons-Moll
Project: virtualhumans.mpi-inf.mpg.de/MVGBench/
By Xianghui Xie, Jan Eric Lenssen, Gerard Pons-Moll
Project: virtualhumans.mpi-inf.mpg.de/MVGBench/
October 19, 2025 at 7:49 AM
MVGBench: “A Comprehensive Benchmark for Multi-view Generation Models” — measures 3D consistency & image quality for fair comparisons.
By Xianghui Xie, Jan Eric Lenssen, Gerard Pons-Moll
Project: virtualhumans.mpi-inf.mpg.de/MVGBench/
By Xianghui Xie, Jan Eric Lenssen, Gerard Pons-Moll
Project: virtualhumans.mpi-inf.mpg.de/MVGBench/
VITAL: “More Understandable Feature Visualization via Distribution Alignment & Relevant Information Flow.” Fewer artifacts, more faithful internals, scales well.
By Ada Görgün, Bernt Schiele, Jonas Fischer
Project: adagorgun.github.io/VITAL-Project/
By Ada Görgün, Bernt Schiele, Jonas Fischer
Project: adagorgun.github.io/VITAL-Project/
October 19, 2025 at 7:49 AM
VITAL: “More Understandable Feature Visualization via Distribution Alignment & Relevant Information Flow.” Fewer artifacts, more faithful internals, scales well.
By Ada Görgün, Bernt Schiele, Jonas Fischer
Project: adagorgun.github.io/VITAL-Project/
By Ada Görgün, Bernt Schiele, Jonas Fischer
Project: adagorgun.github.io/VITAL-Project/
AIM (Highlight 🎉): “Amending Inherent Interpretability via Self-Supervised Masking.” - Promotes genuine features over spurious ones—no extra annotations.
By Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper
By Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper
October 19, 2025 at 7:49 AM
AIM (Highlight 🎉): “Amending Inherent Interpretability via Self-Supervised Masking.” - Promotes genuine features over spurious ones—no extra annotations.
By Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper
By Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper
DIY-SC: “Do It Yourself—Learning Semantic Correspondence from Pseudo-Labels.” - Light-weight adapter on DINOv2 / SD+DINOv2 → SOTA on SPair-71k w/o keypoints.
By O. Dünkel, T. Wimmer, C. Theobalt, C. Rupprecht, A. Kortylewski
Page: genintel.github.io/DIY-SC
By O. Dünkel, T. Wimmer, C. Theobalt, C. Rupprecht, A. Kortylewski
Page: genintel.github.io/DIY-SC
October 19, 2025 at 7:49 AM
DIY-SC: “Do It Yourself—Learning Semantic Correspondence from Pseudo-Labels.” - Light-weight adapter on DINOv2 / SD+DINOv2 → SOTA on SPair-71k w/o keypoints.
By O. Dünkel, T. Wimmer, C. Theobalt, C. Rupprecht, A. Kortylewski
Page: genintel.github.io/DIY-SC
By O. Dünkel, T. Wimmer, C. Theobalt, C. Rupprecht, A. Kortylewski
Page: genintel.github.io/DIY-SC
ICCV 2025 🌺 Aloha from Hawaii! MPI-INF (D2) is presenting 4 papers this year (one Highlight). Thread 👇
October 19, 2025 at 7:49 AM
ICCV 2025 🌺 Aloha from Hawaii! MPI-INF (D2) is presenting 4 papers this year (one Highlight). Thread 👇
Reposted by Computer Vision and Machine Learning at MPI Informatics
Are you using DINOv2 for tasks that require semantic features? DIY-SC might be the alternative!
It refines DINOv2 or SD+DINOv2 features and achieves a new SOTA on the semantic correspondence dataset SPair-71k when not relying on annotated keypoints! [1/6]
genintel.github.io/DIY-SC
It refines DINOv2 or SD+DINOv2 features and achieves a new SOTA on the semantic correspondence dataset SPair-71k when not relying on annotated keypoints! [1/6]
genintel.github.io/DIY-SC
June 26, 2025 at 12:56 PM
Are you using DINOv2 for tasks that require semantic features? DIY-SC might be the alternative!
It refines DINOv2 or SD+DINOv2 features and achieves a new SOTA on the semantic correspondence dataset SPair-71k when not relying on annotated keypoints! [1/6]
genintel.github.io/DIY-SC
It refines DINOv2 or SD+DINOv2 features and achieves a new SOTA on the semantic correspondence dataset SPair-71k when not relying on annotated keypoints! [1/6]
genintel.github.io/DIY-SC
Reposted by Computer Vision and Machine Learning at MPI Informatics
Super excited to introduce
✨ AnyUp: Universal Feature Upsampling 🔎
Upsample any feature - really any feature - with the same upsampler, no need for cumbersome retraining.
SOTA feature upsampling results while being feature-agnostic at inference time.
🌐 wimmerth.github.io/anyup/
✨ AnyUp: Universal Feature Upsampling 🔎
Upsample any feature - really any feature - with the same upsampler, no need for cumbersome retraining.
SOTA feature upsampling results while being feature-agnostic at inference time.
🌐 wimmerth.github.io/anyup/
October 16, 2025 at 9:07 AM
Super excited to introduce
✨ AnyUp: Universal Feature Upsampling 🔎
Upsample any feature - really any feature - with the same upsampler, no need for cumbersome retraining.
SOTA feature upsampling results while being feature-agnostic at inference time.
🌐 wimmerth.github.io/anyup/
✨ AnyUp: Universal Feature Upsampling 🔎
Upsample any feature - really any feature - with the same upsampler, no need for cumbersome retraining.
SOTA feature upsampling results while being feature-agnostic at inference time.
🌐 wimmerth.github.io/anyup/
Reposted by Computer Vision and Machine Learning at MPI Informatics
🚨 Call for Questions! 🚨
We are inviting the community and the stakeholders to submit questions, which will be discussed with our experts at the workshop! 🎤💡
👉 Submit your questions: forms.gle/8cYb4Ce3dGHi...
Workshop: excv-workshop.github.io
@iccv.bsky.social
#ICCV2025 #eXCV
We are inviting the community and the stakeholders to submit questions, which will be discussed with our experts at the workshop! 🎤💡
👉 Submit your questions: forms.gle/8cYb4Ce3dGHi...
Workshop: excv-workshop.github.io
@iccv.bsky.social
#ICCV2025 #eXCV
September 8, 2025 at 3:54 PM
🚨 Call for Questions! 🚨
We are inviting the community and the stakeholders to submit questions, which will be discussed with our experts at the workshop! 🎤💡
👉 Submit your questions: forms.gle/8cYb4Ce3dGHi...
Workshop: excv-workshop.github.io
@iccv.bsky.social
#ICCV2025 #eXCV
We are inviting the community and the stakeholders to submit questions, which will be discussed with our experts at the workshop! 🎤💡
👉 Submit your questions: forms.gle/8cYb4Ce3dGHi...
Workshop: excv-workshop.github.io
@iccv.bsky.social
#ICCV2025 #eXCV
Reposted by Computer Vision and Machine Learning at MPI Informatics
Kurt Mehlhorn, Founding Director of MPI for Informatics, was awarded the Saarland Order of Merit yesterday by Minister President Anke Rehlinger. The award recognizes his life’s work, from advancing algorithmic research to mentoring researchers and helping build key institutions. More: sic.link/merit
Kurt Mehlhorn awarded the Saarland Order of Merit
Minister President Rehlinger presented the order during a ceremonial event at the Saarland State Chancellery.
sic.link
August 21, 2025 at 8:02 AM
Kurt Mehlhorn, Founding Director of MPI for Informatics, was awarded the Saarland Order of Merit yesterday by Minister President Anke Rehlinger. The award recognizes his life’s work, from advancing algorithmic research to mentoring researchers and helping build key institutions. More: sic.link/merit
Reposted by Computer Vision and Machine Learning at MPI Informatics
Are you an XAI researcher attending #ICCV2025? Submit your recently published work — at CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI etc. — to the eXCV Workshop for the opportunity to further showcase your work! Published papers can be submitted as is, no rewriting necessary.
@iccv.bsky.social
@iccv.bsky.social
August 14, 2025 at 10:36 AM
Are you an XAI researcher attending #ICCV2025? Submit your recently published work — at CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI etc. — to the eXCV Workshop for the opportunity to further showcase your work! Published papers can be submitted as is, no rewriting necessary.
@iccv.bsky.social
@iccv.bsky.social
Reposted by Computer Vision and Machine Learning at MPI Informatics
🚀 UTD is now fully released!
Code ✅ Models ✅ 2M video descriptions ✅ Debiased splits for 12 datasets ✅
Everything you need to benchmark video models more fairly is now public:
🔗 github.com/ninatu/utd-p...
🎥 Let’s make video understanding actually about video understanding.
Code ✅ Models ✅ 2M video descriptions ✅ Debiased splits for 12 datasets ✅
Everything you need to benchmark video models more fairly is now public:
🔗 github.com/ninatu/utd-p...
🎥 Let’s make video understanding actually about video understanding.
August 8, 2025 at 8:45 AM
🚀 UTD is now fully released!
Code ✅ Models ✅ 2M video descriptions ✅ Debiased splits for 12 datasets ✅
Everything you need to benchmark video models more fairly is now public:
🔗 github.com/ninatu/utd-p...
🎥 Let’s make video understanding actually about video understanding.
Code ✅ Models ✅ 2M video descriptions ✅ Debiased splits for 12 datasets ✅
Everything you need to benchmark video models more fairly is now public:
🔗 github.com/ninatu/utd-p...
🎥 Let’s make video understanding actually about video understanding.
Reposted by Computer Vision and Machine Learning at MPI Informatics
People often use synthetic corruptions to test model robustness, but do these reflect real-world challenges?
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
July 24, 2025 at 9:16 AM
People often use synthetic corruptions to test model robustness, but do these reflect real-world challenges?
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
Reposted by Computer Vision and Machine Learning at MPI Informatics
🚨Deadline Extension Alert!
Our Non-proceedings track is open till August 15th for the eXCV workshop at ICCV.
Our nectar track accepts published papers, as is.
More info at: excv-workshop.github.io
@iccv.bsky.social #ICCV2025
Our Non-proceedings track is open till August 15th for the eXCV workshop at ICCV.
Our nectar track accepts published papers, as is.
More info at: excv-workshop.github.io
@iccv.bsky.social #ICCV2025
July 18, 2025 at 9:31 AM
🚨Deadline Extension Alert!
Our Non-proceedings track is open till August 15th for the eXCV workshop at ICCV.
Our nectar track accepts published papers, as is.
More info at: excv-workshop.github.io
@iccv.bsky.social #ICCV2025
Our Non-proceedings track is open till August 15th for the eXCV workshop at ICCV.
Our nectar track accepts published papers, as is.
More info at: excv-workshop.github.io
@iccv.bsky.social #ICCV2025
Reposted by Computer Vision and Machine Learning at MPI Informatics
⏳Still need to wait for your last experiment results?
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
July 24, 2025 at 6:20 AM
⏳Still need to wait for your last experiment results?
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
4/ "🌀Spatial Reasoners for Continuous Variables in Any Domains" by @bartpog.bsky.social, @chriswewer.bsky.social, Bernt Schiele, and @janericlenssen.bsky.social (CODEML Workshop)
🔍 Software framework for training Spatial Reasoning Models in any domain
🔍 Software framework for training Spatial Reasoning Models in any domain
July 13, 2025 at 8:00 AM
4/ "🌀Spatial Reasoners for Continuous Variables in Any Domains" by @bartpog.bsky.social, @chriswewer.bsky.social, Bernt Schiele, and @janericlenssen.bsky.social (CODEML Workshop)
🔍 Software framework for training Spatial Reasoning Models in any domain
🔍 Software framework for training Spatial Reasoning Models in any domain
🔍 Can you really trust the explanations your classifier gives you? We show which pixels in the input are provably important to the classifier’s prediction within a radius around the input.
📄 openreview.net/pdf?id=NngoE...
🔗 github.com/AlaaAnani/ce...
📄 openreview.net/pdf?id=NngoE...
🔗 github.com/AlaaAnani/ce...
openreview.net
July 13, 2025 at 8:00 AM
🔍 Can you really trust the explanations your classifier gives you? We show which pixels in the input are provably important to the classifier’s prediction within a radius around the input.
📄 openreview.net/pdf?id=NngoE...
🔗 github.com/AlaaAnani/ce...
📄 openreview.net/pdf?id=NngoE...
🔗 github.com/AlaaAnani/ce...
3/ "Pixel-level Certified Explanations via Randomized Smoothing" by @aanani.bsky.social, Tobias Lorenz, Mario Fritz, and Bernt Schiele
July 13, 2025 at 8:00 AM
3/ "Pixel-level Certified Explanations via Randomized Smoothing" by @aanani.bsky.social, Tobias Lorenz, Mario Fritz, and Bernt Schiele
