3 papers
cs.CV2024
PReP: Efficient context-based shape retrieval for missing parts
Vlassis Fotis, Ioannis Romanelis, Georgios Mylonas +2
In this paper we study the problem of shape part retrieval in the point cloud domain. Shape retrieval methods in the literature rely on the presence of an existing query object, bu…
cs.CV2024
Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
Ioannis Romanelis, Vlassios Fotis, Athanasios Kalogeras +3
We propose a novel point cloud U-Net diffusion architecture for 3D generative modeling capable of generating high-quality and diverse 3D shapes while maintaining fast generation ti…
cs.CV2024
ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers
Ioannis Romanelis, Vlassis Fotis, Konstantinos Moustakas +1
In this paper we delve into the properties of transformers, attained through self-supervision, in the point cloud domain. Specifically, we evaluate the effectiveness of Masked Auto…