11 papers
Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
Lisa Weijler, Irene Ballester, Guofeng Mei +2
Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models operate purely in a feed-fo…
Action-guided generation of 3D functionality segmentation data
Jaime Corsetti, Francesco Giuliari, Davide Boscaini +6
3D functionality segmentation aims to identify the interactive element in a 3D scene required to perform an action described in free-form language (e.g., the handle to ``Open the s…
The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report
Bin Ren, Hang Guo, Yan Shu +60
This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a…
Efficient Encoder-Free Fourier-based 3D Large Multimodal Model
Guofeng Mei, Wei Lin, Luigi Riz +3
Large Multimodal Models (LMMs) that process 3D data typically rely on heavy, pre-trained visual encoders to extract geometric features. While recent 2D LMMs have begun to eliminate…
GLASS: Graph and Vision-Language Assisted Semantic Shape Correspondence
Qinfeng Xiao, Guofeng Mei, Qilong Liu +5
Establishing dense correspondence across 3D shapes is crucial for fundamental downstream tasks, including texture transfer, shape interpolation, and robotic manipulation. However,…
Obstruction reasoning for robotic grasping
Runyu Jiao, Matteo Bortolon, Francesco Giuliari +5
Successful robotic grasping in cluttered environments not only requires a model to visually ground a target object but also to reason about obstructions that must be cleared before…