activity
20242026
most citedData Leakage Detection and De-duplication in Large Scale Geospatial Image Datasets

3 citations · 4 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CG20261 cited

EASE: Parametric garment design with explicit and local ease control

Kristijan Bartol, Frieda Hentschel, Nataliya Sadretdinova +4

Garment fit and comfort depend critically on ease, the local allowance of excess material relative to the body. In existing design pipelines, ease is typically a byproduct of geome…

cs.CV20263 cited

Data Leakage Detection and De-duplication in Large Scale Geospatial Image Datasets

Yeshwanth Kumar Adimoolam, Charalambos Poullis, Melinos Averkiou

In our study, we conducted a comprehensive analysis of three widely used datasets in the domain of building footprint extraction using deep neural networks: the INRIA Aerial Image…

cs.GR2025

Im2SurfTex: Surface Texture Generation via Neural Backprojection of Multi-View Images

Yiangos Georgiou, Marios Loizou, Melinos Averkiou +1

We present Im2SurfTex, a method that generates textures for input 3D shapes by learning to aggregate multi-view image outputs produced by 2D image diffusion models onto the shapes'…

cs.CV2025

ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts

Dmitry Petrov, Pradyumn Goyal, Divyansh Shivashok +3

We introduce ShapeWords, an approach for synthesizing images based on 3D shape guidance and text prompts. ShapeWords incorporates target 3D shape information within specialized tok…

cs.CV2024

Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery

Yeshwanth Kumar Adimoolam, Charalambos Poullis, Melinos Averkiou

Extraction of building footprint polygons from remotely sensed data is essential for several urban understanding tasks such as reconstruction, navigation, and mapping. Despite sign…

cs.CV2024

GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis

Dmitry Petrov, Pradyumn Goyal, Vikas Thamizharasan +5

We introduce GEM3D -- a new deep, topology-aware generative model of 3D shapes. The key ingredient of our method is a neural skeleton-based representation encoding information on b…