1 citations · 1 across the 1 of their papers we have counts for
15 papers
MiraGe: Editable 2D Images using Gaussian Splatting
Joanna WaczyÅska, Tomasz Szczepanik, Piotr Borycki +3
Implicit Neural Representations (INRs) approximate discrete data through continuous functions and are commonly used for encoding 2D images. Traditional image-based INRs employ neur…
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
Piotr Borycki, Magdalena TrÄdowicz, Jacek Tabor +2
Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive "this looks like that" reasoning paradigm. On the other hand,…
APEX: Audio Prototype EXplanations for Classification Tasks
Piotr Kawa, Kornel Howil, Piotr Borycki +3
Explainable AI (XAI) has achieved remarkable success in image classification, yet the audio domain lacks equally mature solutions. Current methods apply vision-based attribution te…
SMAL-pets: SMAL Based Avatars of Pets from Single Image
Piotr Borycki, Joanna WaczyÅska, Yizhe Zhu +2
Creating high-fidelity, animatable 3D dog avatars remains a formidable challenge in computer vision. Unlike human digital doubles, animal reconstruction faces a critical shortage o…
XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretability
Dominik Galus, Julia Farganus, Tymoteusz Zapala +4
3D Gaussian Splatting (3DGS) has rapidly become a standard for high-fidelity 3D reconstruction, yet its adoption in multiple critical domains is hindered by the lack of interpretab…
DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models
Alicja Polowczyk, Agnieszka Polowczyk, Piotr Borycki +3
Despite impressive results from recent text-to-image models like FLUX, visual and anatomical artifacts remain a significant hurdle for practical and professional use. Existing meth…