Open scene understanding: Grounded situation recognition meets segment anything for hel** people with visual impairments

R Liu, J Zhang, K Peng, J Zheng… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Grounded Situation Recognition (GSR) is capable of recognizing and interpreting
visual scenes in a contextually intuitive way, yielding salient activities (verbs) and the …

Open panoramic segmentation

J Zheng, R Liu, Y Chen, K Peng, C Wu, K Yang… - … on Computer Vision, 2024 - Springer
Panoramic images, capturing a 360∘ field of view (FoV), encompass omnidirectional spatial
information crucial for scene understanding. However, it is not only costly to obtain training …

Mapa: Text-driven photorealistic material painting for 3d shapes

S Zhang, S Peng, T Xu, Y Yang, T Chen… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing
methods that synthesize texture maps, we propose to generate segment-wise procedural …

Referring atomic video action recognition

K Peng, J Fu, K Yang, D Wen, Y Chen, R Liu… - … on Computer Vision, 2024 - Springer
We introduce a new task called R eferring A tomic V ideo A ction R ecognition (RAVAR),
aimed at identifying atomic actions of a particular person based on a textual description and …

Atmospheric transmission and thermal inertia induced blind road segmentation with a large-scale dataset tbrsd

J Chen, X Bai - Proceedings of the IEEE/CVF International …, 2023 - openaccess.thecvf.com
Computer vision-based walking assistants are prominent tools for aiding visually impaired
people in navigation. Blind road segmentation is a key element in these walking assistant …

One-shot recognition of any material anywhere using contrastive learning with physics-based rendering

MS Drehwald, S Eppel, J Li, H Hao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Visual recognition of materials and their states is essential for understanding the world, from
determining whether food is cooked, metal is rusted, or a chemical reaction has occurred …

FrictionSegNet: Simultaneous Semantic Segmentation and Friction Estimation Using Hierarchical Latent Variable Models

M Otoofi, L Laine, L Henderson… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
This paper presents an end-to-end approach, named FrictionSegNet, for jointly estimating
tyre-road friction coefficient and identifying road surfaces in real time from on board camera …

Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data

S Eppel, J Li, M Drehwald, A Aspuru-Guzik - arxiv preprint arxiv …, 2024 - arxiv.org
Visual understanding and segmentation of materials and their states is fundamental for
understanding the physical world. The infinite textures, shapes and often blurry boundaries …