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 generative pathway, so one edit must cover geometry and texture at once. Native 3D generators, which synthesize structured 3D representations d...
Karol Dziekan, P. Spurek, Dawid Malarz· 0 citations
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 missing geometry and holes in the reconstructed scene. Existing methods often rely on generative models to complete such regions. However,...
W. Jakubowska, Maciej Zięba, P. Spurek· 0 citations
Leading multi-bit watermarking methods for language models encode messages by biasing the model's next-token probabilities, creating a trade-off between message recovery and text quality. Their decoders typically return the highest-scoring candidate from accumulated token-level evidence, without a certified abstention...
Pawel Batorski, P. Spurek, Paul Swoboda· 0 citations
Experiments across standard reconstruction benchmarks demonstrate competitive rendering quality while using a compact set of primitives and establish FlaRe as a versatile representation that brings high-fidelity neural rendering, ray-tracing, geometric manipulation, and appearance editing into a unified scene model.
K. Byrski, Rafał Tobiasz, Grzegorz Wilczynski et al.· 0 citations
OmniStyle-INR is introduced, a novel framework that leverages network-based continuous representations as a truly universal domain that performs high-quality style transfer across all visual modalities, guided seamlessly by both text prompts and visual exemplars.
Rafał Kajca, Michał Miziołek, Kornel Howil et al.· arXiv.org· 0 citations
This work proposes a novel one-shot unlearning approach, abandoning iterative optimization in favor of a direct, exact analytical solution, and achieves state-of-the-art forgetting-utility trade-offs on TOFU-5%, TOFU-10%, MUSE-Books, MUSE-News and WMDP, significantly reducing computational overhead without sacrificing...
Pawel Batorski, P. Spurek, Paul Swoboda· 1 citation
TOM-GS is introduced, an editable video representation that forgoes complex deformations in favor of regular 3D Gaussians equipped with a continuous temporal opacity formulation, which enables static 3D spatial components to fade smoothly in and out of the scene.
Marek Lisowski, Łukasz Smoliński, Kornel Howil et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
