English
Related papers

Related papers: Lexicon3D: Probing Visual Foundation Models for Co…

200 papers

In this work, we interpret the representations of multi-object scenes in vision encoders through the lens of structured representations. Structured representations allow modeling of individual objects distinctly and their flexible use based…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Tarun Khajuria , Braian Olmiro Dias , Marharyta Domnich , Jaan Aru

3D visual grounding (3DVG) is a critical task in scene understanding that aims to identify objects in 3D scenes based on text descriptions. However, existing methods rely on separately pre-trained vision and text encoders, resulting in a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Yinuo Zheng , Lipeng Gu , Honghua Chen , Liangliang Nan , Mingqiang Wei

Images depicting complex, dynamic scenes are challenging to parse automatically, requiring both high-level comprehension of the overall situation and fine-grained identification of participating entities and their interactions. Current…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Shahaf Pruss , Morris Alper , Hadar Averbuch-Elor

Foundation models or pre-trained models have substantially improved the performance of various language, vision, and vision-language understanding tasks. However, existing foundation models can only perform the best in one type of tasks,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Xinsong Zhang , Yan Zeng , Jipeng Zhang , Hang Li

The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialised domains such…

Existing research on 3D Large Language Models (LLMs) still struggles to achieve grounded question-answering, primarily due to the under-exploration of the mechanism of human-like scene-object grounded reasoning. This paper bridges the gap…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Xiongkun Linghu , Jiangyong Huang , Ziyu Zhu , Baoxiong Jia , Siyuan Huang

Recent advances in large vision-language models (VLMs) have shown significant promise for 3D scene understanding. Existing VLM-based approaches typically align 3D scene features with the VLM's embedding space. However, this implicit…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Chen Li , Eric Peh , Basura Fernando

In contrast to numerous NLP and 2D vision foundational models, learning a 3D foundational model poses considerably greater challenges. This is primarily due to the inherent data variability and diversity of downstream tasks. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Haoyi Zhu , Honghui Yang , Xiaoyang Wu , Di Huang , Sha Zhang , Xianglong He , Hengshuang Zhao , Chunhua Shen , Yu Qiao , Tong He , Wanli Ouyang

Vision Foundation Models (VFMs) and Vision Language Models (VLMs) have revolutionized computer vision by providing rich semantic and geometric representations. This paper presents a comprehensive visual comparison between CLIP based and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Md Selim Sarowar , Sungho Kim

The lack of a large-scale 3D-text corpus has led recent works to distill open-vocabulary knowledge from vision-language models (VLMs). However, these methods typically rely on a single VLM to align the feature spaces of 3D models within a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Jinlong Li , Cristiano Saltori , Fabio Poiesi , Nicu Sebe

Scene understanding and reasoning has been a fundamental problem in 3D computer vision, requiring models to identify objects, their properties, and spatial or comparative relationships among the objects. Existing approaches enable this by…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Vivek Madhavaram , Vartika Sengar , Arkadipta De , Charu Sharma

With the growing adoption of vision-language-action models and world models in autonomous driving systems, scalable image tokenization becomes crucial as the interface for the visual modality. However, most existing tokenizers are designed…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Dong Zhuo , Wenzhao Zheng , Sicheng Zuo , Siming Yan , Lu Hou , Jie Zhou , Jiwen Lu

Accurate 3D scene reconstruction is essential for numerous medical tasks. Given the challenges in obtaining ground truth data, there has been an increasing focus on self-supervised learning (SSL) for endoscopic depth estimation as a basis…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Beilei Cui , Long Bai , Mobarakol Islam , An Wang , Zhiqi Ma , Yiming Huang , Feng Li , Zhen Chen , Zhongliang Jiang , Nassir Navab , Hongliang Ren

Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based…

Computer Vision and Pattern Recognition · Computer Science 2015-07-22 Baoguang Shi , Xiang Bai , Cong Yao

Understanding and reasoning about complex 3D environments requires structured scene representations that capture not only objects but also their semantic and spatial relationships. While recent works on 3D scene graph generation have…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Pranav Saxena , Jimmy Chiun

Segmenting long-form videos into semantically coherent scenes is a fundamental task in large-scale video understanding. Existing encoder-based methods are limited by visual-centric biases, classify each shot in isolation without leveraging…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Nimrod Berman , Adam Botach , Emanuel Ben-Baruch , Shunit Haviv Hakimi , Asaf Gendler , Ilan Naiman , Erez Yosef , Igor Kviatkovsky

The rise of vision-language foundation models marks an advancement in bridging the gap between human and machine capabilities in 3D scene reasoning. Existing 3D reasoning benchmarks assume real-time scene accessibility, which is impractical…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Ye Mao , Weixun Luo , Junpeng Jing , Anlan Qiu , Krystian Mikolajczyk

In this paper, we propose VideoLLaMA3, a more advanced multimodal foundation model for image and video understanding. The core design philosophy of VideoLLaMA3 is vision-centric. The meaning of "vision-centric" is two-fold: the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Boqiang Zhang , Kehan Li , Zesen Cheng , Zhiqiang Hu , Yuqian Yuan , Guanzheng Chen , Sicong Leng , Yuming Jiang , Hang Zhang , Xin Li , Peng Jin , Wenqi Zhang , Fan Wang , Lidong Bing , Deli Zhao

Videos are continuous 2D projections of 3D worlds. After training on large video data, will global 3D understanding naturally emerge? We study this by quantifying the 3D understanding of existing Video Foundation Models (VidFMs) pretrained…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Zixuan Huang , Xiang Li , Zhaoyang Lv , James M. Rehg

Holistic 3D scene understanding entails estimation of both layout configuration and object geometry in a 3D environment. Recent works have shown advances in 3D scene estimation from various input modalities (e.g., images, 3D scans), by…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Yinyu Nie , Angela Dai , Xiaoguang Han , Matthias Nießner