Konstantinos G. Derpanis

York University — Canada

Computer Science · Physical Sciences

28h-index4.7kcitations126works3.62yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(45), Human Pose and Action Recognition(34), Advanced Neural Network Applications(24), Advanced Image and Video Retrieval Techniques(22), Generative Adversarial Networks and Image Synthesis(20)

Publications126 total

Comparing Deep Neural Network Architectures as Models of Human Lightness and Illusion Perception.
Journal of Vision·2025Open Access
LSE-NeRF: Learning Sensor Modeling Errors for Deblured Neural Radiance Fields with RGB-Event Stereo
2025· 1 cited
Revisiting Image Fusion for Multi-Illuminant White-Balance Correction
arXiv (Cornell University)·2025Open Access
Geometry-Aware Diffusion Models for Multiview Scene Inpainting
arXiv (Cornell University)·2025Open Access
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
arXiv (Cornell University)·2025· 1 citedOpen Access
PolyOculus: Simultaneous Multi-view Image-Based Novel View Synthesis
Lecture notes in computer science·2024· 1 cited
Watch Your Steps: Local Image and Scene Editing by Text Instructions
Lecture notes in computer science·2024· 19 cited
Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024· 1 cited
Lightness Illusions Through AI Eyes: Assessing ConvNet and ViT Concordance with Human Perception
Journal of Vision·2024Open Access
Visual Concept Connectome (VCC): Open World Concept Discovery and Their Interlayer Connections in Deep Models
2024· 2 cited
Understanding Video Transformers via Universal Concept Discovery
2024· 4 cited
Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
International Journal of Computer Vision·2024· 24 cited
Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models
arXiv (Cornell University)·2024Open Access
PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis
arXiv (Cornell University)·2024Open Access
Understanding Video Transformers via Universal Concept Discovery
arXiv (Cornell University)·2024· 1 citedOpen Access
Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations
arXiv (Cornell University)·2023Open Access
GePSAn: Generative Procedure Step Anticipation in Cooking Videos
arXiv (Cornell University)·2023Open Access
Reference-guided Controllable Inpainting of Neural Radiance Fields
2023· 23 cited
GePSAn: Generative Procedure Step Anticipation in Cooking Videos
2023· 4 cited
Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models
2023· 20 cited
page 1 of 7Next →

Frequent Co-authors

Richard P. Wildes(12), Kostas Daniilidis(11), Xiaowei Zhou(7), Georgios Pavlakos(6), Marcus A. Brubaker(6), Adam W. Harley(5), John K. Tsotsos(5), Matthew Kowal(5), Neil D. B. Bruce(5), Menglong Zhu(4), Jason J. Yu(4), Mikhail Sizintsev(4), Md Amirul Islam(4), Sen Jia(4), Ashkan Mirzaei(3), Tristan Aumentado‐Armstrong(3), Igor Gilitschenski(3), Alex Levinshtein(3), Rainer Herpers(3), Nikita Dvornik(3)