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…
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…
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…
Multimodal Fusion SLAM with Fourier Attention
Youjie Zhou, Guofeng Mei, Yiming Wang +2
Visual SLAM is particularly challenging in environments affected by noise, varying lighting conditions, and darkness. Learning-based optical flow algorithms can leverage multiple m…
Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenization
Guofeng Mei, Qinfeng Xiao, Bin Ren +7
Vision-language models, such as CLIP, encode rich semantic knowledge through large-scale image-text pretraining. Reusing these models for 3D understanding is highly desirable, beca…
Free-form language-based robotic reasoning and grasping
Runyu Jiao, Alice Fasoli, Francesco Giuliari +5
Performing robotic grasping from a cluttered bin based on human instructions is a challenging task, as it requires understanding both the nuances of free-form language and the spat…
PerLA: Perceptive 3D Language Assistant
Guofeng Mei, Wei Lin, Luigi Riz +3
Enabling Large Language Models (LLMs) to understand the 3D physical world is an emerging yet challenging research direction. Current strategies for processing point clouds typicall…
Vocabulary-Free 3D Instance Segmentation with Vision and Language Assistant
Guofeng Mei, Luigi Riz, Yiming Wang +1
Most recent 3D instance segmentation methods are open vocabulary, offering a greater flexibility than closed-vocabulary methods. Yet, they are limited to reasoning within a specifi…