76 citations · 257 across the 98 of their papers we have counts for
19 papers · 2 filters
CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork
Wojciech Gromski, Patryk Krukowski, Jan Miksa +2
Continual personalization of text-to-image diffusion models requires sequentially acquiring new concepts while retaining previously learned ones. However, existing methods either s…
STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models
Karol Dziekan, Przemysław Spurek, Dawid Malarz
Concept erasure suppresses a target concept while preserving behavior on unrelated inputs. Existing closed-form methods were designed for 2D image diffusion and assume a single gen…
FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning
Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk +1
The rapid advancement of generative video models has enabled the synthesis of increasingly realistic and temporally coherent videos, while also raising concerns about the generatio…
ORCA: Occlusion-Aware Refinement and Completion for Novel View Synthesis
Weronika Jakubowska, Maciej Zięba, Przemysław Spurek
Novel-view synthesis from a single image is a fundamentally ambiguous problem. As the camera moves away from the input viewpoint, previously hidden regions become visible, exposing…
PiPS: Post-Hoc Prototypical Explanations for Interpretable Semantic Segmentation
Miłosz Adamczyk, Tymoteusz Zapala, Piotr Borycki +1
With the increasing deployment of deep neural networks in critical systems, such as medical diagnostics and autonomous vehicles, ensuring their interpretability is crucial to build…
COGENT: Counterfactual Gaussian Explanations for Volumetric Medical Images
Dorian Rząsa, Bartosz Zabdyr, Krzysztof Piekarz +7
Explainability is essential for deploying deep learning models in high-stakes medical applications. Existing explainability methods for volumetric imaging predominantly operate in…
Floating Radiance Networks
Krzysztof Byrski, Rafał Tobiasz, Grzegorz Wilczyński +5
Recent advances in neural scene representations enable photorealistic novel-view synthesis, yet most methods remain tightly coupled to a single rendering paradigm, limiting their v…
TOM-GS: Editable Video Representation via Temporal Opacity Modulation of Static 3D Gaussians
Marek Lisowski, Łukasz Smoliński, Kornel Howil +3
While Implicit Neural Representations (INRs) and dynamic 3D Gaussian Splatting (3DGS) achieve impressive results in video processing, they often fall short of producing representat…
OmniStyle-INR: Universal and Multimodal Style Transfer for INRs
Rafał Kajca, Michał Miziołek, Kornel Howil +2
Style transfer remains a fundamental and highly important task across various data modalities, enabling creative manipulation conditioned by both reference images and textual descr…
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
Piotr Borycki, Magdalena Trędowicz, 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,…
BARRIER: Bounded Activation Regions for Robust Information Erasure
Jan Miksa, Patryk Krukowski, Przemysław Spurek +2
Machine unlearning aims to remove targeted concepts from a trained model while preserving the rest of its knowledge. Central challenge of this setting is that effective and robust…
SMAL-pets: SMAL Based Avatars of Pets from Single Image
Piotr Borycki, Joanna Waczyńska, 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…
IRIS: Intersection-aware Ray-based Implicit Editable Scenes
Grzegorz Wilczyński, Mikołaj Zieliński, Krzysztof Byrski +3
Neural Radiance Fields achieve high-fidelity scene representation but suffer from costly training and rendering, while 3D Gaussian splatting offers real-time performance with stron…
ColonSplat: Reconstruction of Peristaltic Motion in Colonoscopy with Dynamic Gaussian Splatting
Weronika Smolak-Dyżewska, Joanna Kaleta, Diego Dall'Alba +1
Accurate 3D reconstruction of colonoscopy data, accounting for complex peristaltic movements, is crucial for advanced surgical navigation and retrospective diagnostics. While recen…
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…
AnyStyle: Single-Pass Multimodal Stylization for 3D Gaussian Splatting
Joanna Kaleta, Bartosz Świrta, Kacper Kania +3
The growing demand for rapid and scalable 3D asset creation has driven interest in feed-forward 3D reconstruction methods, with 3D Gaussian Splatting (3DGS) emerging as an effectiv…
UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning
Piotr Wójcik, Maksym Petrenko, Wojciech Gromski +2
Recent advances in large-scale diffusion models have intensified concerns about their potential misuse, particularly in generating realistic yet harmful or socially disruptive cont…
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…
ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models
Ignacy Kolton, Kacper Marzol, Paweł Batorski +3
Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often…