activity
20242026
most citedCLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting

2 citations · 5 across the 8 of their papers we have counts for

collaborators

11 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.LG2025

Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models

Agnieszka Polowczyk, Alicja Polowczyk, Joanna Waczyńska +2

The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawfu…

cs.GR2025

GS-Verse: Mesh-based Gaussian Splatting for Physics-aware Interaction in Virtual Reality

Anastasiya Pechko, Piotr Borycki, Joanna Waczyńska +4

As the demand for immersive 3D content grows, the need for intuitive and efficient interaction methods becomes paramount. Current techniques for physically manipulating 3D content…

cs.CV2025

HuSc3D: Human Sculpture dataset for 3D object reconstruction

Weronika Smolak-Dyżewska, Dawid Malarz, Grzegorz Wilczyński +4

3D scene reconstruction from 2D images is one of the most important tasks in computer graphics. Unfortunately, existing datasets and benchmarks concentrate on idealized synthetic o…