Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Hanspeter Pfister

Hanspeter Pfister

Robert Krueger and Jared Jessup contributed equally to this work

Revisiting RCAN: Improved Training for Image Super-Resolution


Jan 27, 2022
Zudi Lin, Prateek Garg, Atmadeep Banerjee, Salma Abdel Magid, Deqing Sun, Yulun Zhang, Luc Van Gool, Donglai Wei, Hanspeter Pfister

Figure 1 for Revisiting RCAN: Improved Training for Image Super-Resolution
Figure 2 for Revisiting RCAN: Improved Training for Image Super-Resolution
Figure 3 for Revisiting RCAN: Improved Training for Image Super-Resolution
Figure 4 for Revisiting RCAN: Improved Training for Image Super-Resolution
* 13 pages with 10 tables and 4 figures 
  Access Paper or Ask Questions

PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics


Dec 10, 2021
Zudi Lin, Donglai Wei, Jeff Lichtman, Hanspeter Pfister

Figure 1 for PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics
Figure 2 for PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics
Figure 3 for PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics
Figure 4 for PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics
* Technical report 
  Access Paper or Ask Questions

Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation


Nov 15, 2021
Anirudh S Chakravarthy, Won-Dong Jang, Zudi Lin, Donglai Wei, Song Bai, Hanspeter Pfister

Figure 1 for Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation
Figure 2 for Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation
Figure 3 for Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation
Figure 4 for Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation
* Accepted at CVPR RVSU Workshop 2021 
  Access Paper or Ask Questions

Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss


Oct 30, 2021
Akira Sakai, Taro Sunagawa, Spandan Madan, Kanata Suzuki, Takashi Katoh, Hiromichi Kobashi, Hanspeter Pfister, Pawan Sinha, Xavier Boix, Tomotake Sasaki

Figure 1 for Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss
Figure 2 for Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss
Figure 3 for Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss
Figure 4 for Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss

  Access Paper or Ask Questions

MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification


Oct 27, 2021
Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, Bingbing Ni

Figure 1 for MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification
Figure 2 for MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification
Figure 3 for MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification
Figure 4 for MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification
* The data and code are publicly available at https://medmnist.com/. arXiv admin note: text overlap with arXiv:2010.14925 
  Access Paper or Ask Questions

GenNI: Human-AI Collaboration for Data-Backed Text Generation


Oct 19, 2021
Hendrik Strobelt, Jambay Kinley, Robert Krueger, Johanna Beyer, Hanspeter Pfister, Alexander M. Rush

Figure 1 for GenNI: Human-AI Collaboration for Data-Backed Text Generation
Figure 2 for GenNI: Human-AI Collaboration for Data-Backed Text Generation
Figure 3 for GenNI: Human-AI Collaboration for Data-Backed Text Generation
Figure 4 for GenNI: Human-AI Collaboration for Data-Backed Text Generation
* IEEE VIS 2021 
  Access Paper or Ask Questions

Scope2Screen: Focus+Context Techniques for Pathology Tumor Assessment in Multivariate Image Data


Oct 10, 2021
Jared Jessup, Robert Krueger, Simon Warchol, John Hoffer, Jeremy Muhlich, Cecily C. Ritch, Giorgio Gaglia, Shannon Coy, Yu-An Chen, Jia-Ren Lin, Sandro Santagata, Peter K. Sorger, Hanspeter Pfister

Figure 1 for Scope2Screen: Focus+Context Techniques for Pathology Tumor Assessment in Multivariate Image Data
Figure 2 for Scope2Screen: Focus+Context Techniques for Pathology Tumor Assessment in Multivariate Image Data
Figure 3 for Scope2Screen: Focus+Context Techniques for Pathology Tumor Assessment in Multivariate Image Data
Figure 4 for Scope2Screen: Focus+Context Techniques for Pathology Tumor Assessment in Multivariate Image Data

  Access Paper or Ask Questions

To Which Out-Of-Distribution Object Orientations Are DNNs Capable of Generalizing?


Sep 28, 2021
Avi Cooper, Xavier Boix, Daniel Harari, Spandan Madan, Hanspeter Pfister, Tomotake Sasaki, Pawan Sinha

Figure 1 for To Which Out-Of-Distribution Object Orientations Are DNNs Capable of Generalizing?
Figure 2 for To Which Out-Of-Distribution Object Orientations Are DNNs Capable of Generalizing?
Figure 3 for To Which Out-Of-Distribution Object Orientations Are DNNs Capable of Generalizing?
Figure 4 for To Which Out-Of-Distribution Object Orientations Are DNNs Capable of Generalizing?

  Access Paper or Ask Questions

Asymmetric 3D Context Fusion for Universal Lesion Detection


Sep 17, 2021
Jiancheng Yang, Yi He, Kaiming Kuang, Zudi Lin, Hanspeter Pfister, Bingbing Ni

Figure 1 for Asymmetric 3D Context Fusion for Universal Lesion Detection
Figure 2 for Asymmetric 3D Context Fusion for Universal Lesion Detection
Figure 3 for Asymmetric 3D Context Fusion for Universal Lesion Detection
Figure 4 for Asymmetric 3D Context Fusion for Universal Lesion Detection
* MICCAI 2021. The code and model are available at https://github.com/M3DV/AlignShift 
  Access Paper or Ask Questions

RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans


Sep 17, 2021
Jiancheng Yang, Shixuan Gu, Donglai Wei, Hanspeter Pfister, Bingbing Ni

Figure 1 for RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
Figure 2 for RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
Figure 3 for RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
Figure 4 for RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
* MICCAI 2021. The dataset, code, and model are available at https://github.com/M3DV/RibSeg 
  Access Paper or Ask Questions

Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field


Jul 13, 2021
Stanislav Lukyanenko, Won-Dong Jang, Donglai Wei, Robbert Struyven, Yoon Kim, Brian Leahy, Helen Yang, Alexander Rush, Dalit Ben-Yosef, Daniel Needleman, Hanspeter Pfister

Figure 1 for Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field
Figure 2 for Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field
Figure 3 for Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field
Figure 4 for Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field
* 8.5 pages, to appear in MICCAI 2021 
  Access Paper or Ask Questions

NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter Scale


Jul 13, 2021
Zudi Lin, Donglai Wei, Mariela D. Petkova, Yuelong Wu, Zergham Ahmed, Krishna Swaroop K, Silin Zou, Nils Wendt, Jonathan Boulanger-Weill, Xueying Wang, Nagaraju Dhanyasi, Ignacio Arganda-Carreras, Florian Engert, Jeff Lichtman, Hanspeter Pfister

Figure 1 for NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter Scale
Figure 2 for NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter Scale
Figure 3 for NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter Scale
Figure 4 for NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter Scale
* The two first authors contributed equally. To be published in the proceedings of MICCAI 2021 
  Access Paper or Ask Questions

AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions


Jul 12, 2021
Donglai Wei, Kisuk Lee, Hanyu Li, Ran Lu, J. Alexander Bae, Zequan Liu, Lifu Zhang, Márcia dos Santos, Zudi Lin, Thomas Uram, Xueying Wang, Ignacio Arganda-Carreras, Brian Matejek, Narayanan Kasthuri, Jeff Lichtman, Hanspeter Pfister

Figure 1 for AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions
Figure 2 for AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions
Figure 3 for AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions
Figure 4 for AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions
* The two first authors contributed equally. To be published in the proceedings of MICCAI 2021 
  Access Paper or Ask Questions

Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers


Jun 30, 2021
Spandan Madan, Tomotake Sasaki, Tzu-Mao Li, Xavier Boix, Hanspeter Pfister

Figure 1 for Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers
Figure 2 for Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers
Figure 3 for Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers
Figure 4 for Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers

  Access Paper or Ask Questions

VICE: Visual Identification and Correction of Neural Circuit Errors


May 14, 2021
Felix Gonda, Xueying Wang, Johanna Beyer, Markus Hadwiger, Jeff W. Lichtman, Hanspeter Pfister

Figure 1 for VICE: Visual Identification and Correction of Neural Circuit Errors
Figure 2 for VICE: Visual Identification and Correction of Neural Circuit Errors
Figure 3 for VICE: Visual Identification and Correction of Neural Circuit Errors
Figure 4 for VICE: Visual Identification and Correction of Neural Circuit Errors
* This paper has been accepted for publication and presentation at the 23rd EG Conference on Visualization (EuroVis 2021) 
  Access Paper or Ask Questions

PhotoApp: Photorealistic Appearance Editing of Head Portraits


Mar 13, 2021
Mallikarjun B R, Ayush Tewari, Abdallah Dib, Tim Weyrich, Bernd Bickel, Hans-Peter Seidel, Hanspeter Pfister, Wojciech Matusik, Louis Chevallier, Mohamed Elgharib, Christian Theobalt

Figure 1 for PhotoApp: Photorealistic Appearance Editing of Head Portraits
Figure 2 for PhotoApp: Photorealistic Appearance Editing of Head Portraits
Figure 3 for PhotoApp: Photorealistic Appearance Editing of Head Portraits
Figure 4 for PhotoApp: Photorealistic Appearance Editing of Head Portraits
* http://gvv.mpi-inf.mpg.de/projects/PhotoApp/ 
  Access Paper or Ask Questions

Consistent Recurrent Neural Networks for 3D Neuron Segmentation


Feb 01, 2021
Felix Gonda, Donglai Wei, Hanspeter Pfister

Figure 1 for Consistent Recurrent Neural Networks for 3D Neuron Segmentation
Figure 2 for Consistent Recurrent Neural Networks for 3D Neuron Segmentation
Figure 3 for Consistent Recurrent Neural Networks for 3D Neuron Segmentation
Figure 4 for Consistent Recurrent Neural Networks for 3D Neuron Segmentation

  Access Paper or Ask Questions

Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation


Dec 02, 2020
Won-Dong Jang, Donglai Wei, Xingxuan Zhang, Brian Leahy, Helen Yang, James Tompkin, Dalit Ben-Yosef, Daniel Needleman, Hanspeter Pfister

Figure 1 for Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation
Figure 2 for Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation
Figure 3 for Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation
Figure 4 for Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation
* 9 pages including references, 9 figures, 5 tables, in preparation for journal submission 
  Access Paper or Ask Questions

Monocular Reconstruction of Neural Face Reflectance Fields


Aug 24, 2020
Mallikarjun B R., Ayush Tewari, Tae-Hyun Oh, Tim Weyrich, Bernd Bickel, Hans-Peter Seidel, Hanspeter Pfister, Wojciech Matusik, Mohamed Elgharib, Christian Theobalt

Figure 1 for Monocular Reconstruction of Neural Face Reflectance Fields
Figure 2 for Monocular Reconstruction of Neural Face Reflectance Fields
Figure 3 for Monocular Reconstruction of Neural Face Reflectance Fields
Figure 4 for Monocular Reconstruction of Neural Face Reflectance Fields
* Project page - http://gvv.mpi-inf.mpg.de/projects/FaceReflectanceFields/ 
  Access Paper or Ask Questions

On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations


Jul 15, 2020
Spandan Madan, Timothy Henry, Jamell Dozier, Helen Ho, Nishchal Bhandari, Tomotake Sasaki, Frédo Durand, Hanspeter Pfister, Xavier Boix

Figure 1 for On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations
Figure 2 for On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations
Figure 3 for On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations
Figure 4 for On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations

  Access Paper or Ask Questions

A New Age of Computing and the Brain


Apr 27, 2020
Polina Golland, Jack Gallant, Greg Hager, Hanspeter Pfister, Christos Papadimitriou, Stefan Schaal, Joshua T. Vogelstein

Figure 1 for A New Age of Computing and the Brain
Figure 2 for A New Age of Computing and the Brain
Figure 3 for A New Age of Computing and the Brain
Figure 4 for A New Age of Computing and the Brain
* A Computing Community Consortium (CCC) workshop report, 24 pages 
  Access Paper or Ask Questions

A Topological Nomenclature for 3D Shape Analysis in Connectomics


Sep 27, 2019
Abhimanyu Talwar, Zudi Lin, Donglai Wei, Yuesong Wu, Bowen Zheng, Jinglin Zhao, Won-Dong Jang, Xueying Wang, Jeff W. Lichtman, Hanspeter Pfister

Figure 1 for A Topological Nomenclature for 3D Shape Analysis in Connectomics
Figure 2 for A Topological Nomenclature for 3D Shape Analysis in Connectomics
Figure 3 for A Topological Nomenclature for 3D Shape Analysis in Connectomics
Figure 4 for A Topological Nomenclature for 3D Shape Analysis in Connectomics
* Technical report 
  Access Paper or Ask Questions

White-Box Adversarial Defense via Self-Supervised Data Estimation


Sep 13, 2019
Zudi Lin, Hanspeter Pfister, Ziming Zhang

Figure 1 for White-Box Adversarial Defense via Self-Supervised Data Estimation
Figure 2 for White-Box Adversarial Defense via Self-Supervised Data Estimation
Figure 3 for White-Box Adversarial Defense via Self-Supervised Data Estimation
Figure 4 for White-Box Adversarial Defense via Self-Supervised Data Estimation

  Access Paper or Ask Questions

FDive: Learning Relevance Models using Pattern-based Similarity Measures


Jul 30, 2019
Frederik L. Dennig, Tom Polk, Zudi Lin, Tobias Schreck, Hanspeter Pfister, Michael Behrisch

Figure 1 for FDive: Learning Relevance Models using Pattern-based Similarity Measures
Figure 2 for FDive: Learning Relevance Models using Pattern-based Similarity Measures
Figure 3 for FDive: Learning Relevance Models using Pattern-based Similarity Measures
Figure 4 for FDive: Learning Relevance Models using Pattern-based Similarity Measures
* 12 pages, 7 figures, 2 tables, LaTeX; corrected typo 
  Access Paper or Ask Questions

Visual Interaction with Deep Learning Models through Collaborative Semantic Inference


Jul 24, 2019
Sebastian Gehrmann, Hendrik Strobelt, Robert Krüger, Hanspeter Pfister, Alexander M. Rush

Figure 1 for Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
Figure 2 for Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
Figure 3 for Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
Figure 4 for Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
* IEEE VIS 2019 (VAST) 
  Access Paper or Ask Questions

Fast Mitochondria Segmentation for Connectomics


Dec 14, 2018
Vincent Casser, Kai Kang, Hanspeter Pfister, Daniel Haehn

Figure 1 for Fast Mitochondria Segmentation for Connectomics
Figure 2 for Fast Mitochondria Segmentation for Connectomics
Figure 3 for Fast Mitochondria Segmentation for Connectomics
Figure 4 for Fast Mitochondria Segmentation for Connectomics

  Access Paper or Ask Questions

Detecting Synapse Location and Connectivity by Signed Proximity Estimation and Pruning with Deep Nets


Oct 25, 2018
Toufiq Parag, Daniel Berger, Lee Kamentsky, Benedikt Staffler, Donglai Wei, Moritz Helmstaedter, Jeff W. Lichtman, Hanspeter Pfister

Figure 1 for Detecting Synapse Location and Connectivity by Signed Proximity Estimation and Pruning with Deep Nets
Figure 2 for Detecting Synapse Location and Connectivity by Signed Proximity Estimation and Pruning with Deep Nets
Figure 3 for Detecting Synapse Location and Connectivity by Signed Proximity Estimation and Pruning with Deep Nets
Figure 4 for Detecting Synapse Location and Connectivity by Signed Proximity Estimation and Pruning with Deep Nets

  Access Paper or Ask Questions

Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models


Oct 16, 2018
Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch, Adam Perer, Hanspeter Pfister, Alexander M. Rush

Figure 1 for Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
Figure 2 for Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
Figure 3 for Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
Figure 4 for Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
* VAST - IEEE VIS 2018 
  Access Paper or Ask Questions

Parallel Separable 3D Convolution for Video and Volumetric Data Understanding


Sep 11, 2018
Felix Gonda, Donglai Wei, Toufiq Parag, Hanspeter Pfister

Figure 1 for Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
Figure 2 for Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
Figure 3 for Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
Figure 4 for Parallel Separable 3D Convolution for Video and Volumetric Data Understanding

  Access Paper or Ask Questions

Anisotropic EM Segmentation by 3D Affinity Learning and Agglomeration


Aug 03, 2018
Toufiq Parag, Fabian Tschopp, William Grisaitis, Srinivas C Turaga, Xuewen Zhang, Brian Matejek, Lee Kamentsky, Jeff W. Lichtman, Hanspeter Pfister

Figure 1 for Anisotropic EM Segmentation by 3D Affinity Learning and Agglomeration
Figure 2 for Anisotropic EM Segmentation by 3D Affinity Learning and Agglomeration
Figure 3 for Anisotropic EM Segmentation by 3D Affinity Learning and Agglomeration
Figure 4 for Anisotropic EM Segmentation by 3D Affinity Learning and Agglomeration

  Access Paper or Ask Questions