English
Related papers

Related papers: Thinking with Spatial Code for Physical-World Vide…

200 papers

Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Ilias Stogiannidis , Steven McDonagh , Sotirios A. Tsaftaris

Text-based Visual Question Answering~(TextVQA) aims to produce correct answers for given questions about the images with multiple scene texts. In most cases, the texts naturally attach to the surface of the objects. Therefore, spatial…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Hao Li , Jinfa Huang , Peng Jin , Guoli Song , Qi Wu , Jie Chen

In this work, we address the challenge of encoding speech captured by a microphone array using deep learning techniques with the aim of preserving and accurately reconstructing crucial spatial cues embedded in multi-channel recordings. We…

Sound · Computer Science 2024-07-10 Zhongweiyang Xu , Yong Xu , Vinay Kothapally , Heming Wang , Muqiao Yang , Dong Yu

Visual Language Models (VLMs) have increasingly become the main paradigm for understanding indoor scenes, but they still struggle with metric and spatial reasoning. Current approaches rely on end-to-end video understanding or large-scale…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Fernando Ropero , Erkin Turkoz , Daniel Matos , Junqing Du , Antonio Ruiz , Yanfeng Zhang , Lu Liu , Mingwei Sun , Yongliang Wang

Dynamic scenes contain intricate spatio-temporal information, crucial for mobile robots, UAVs, and autonomous driving systems to make informed decisions. Parsing these scenes into semantic triplets <Subject-Predicate-Object> for accurate…

Computer Vision and Pattern Recognition · Computer Science 2025-05-08 Hang Zhang , Zhuoling Li , Jun Liu

Multimodal Large Language Models (MLLMs) have made impressive progress in connecting vision and language, but they still struggle with spatial understanding and viewpoint-aware reasoning. Recent efforts aim to augment the input…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Kevin Qu , Haozhe Qi , Mihai Dusmanu , Mahdi Rad , Rui Wang , Marc Pollefeys

Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual information. Recently the proposal of ''thinking with images''…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Junfei Wu , Jian Guan , Qiang Liu , Shu Wu , Liang Wang , Wei Wu , Tieniu Tan

Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to associate objects with their properties and spatial relations. Yet it remains unclear where and how such associations…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Kelly Cui , Nikhil Prakash , Ayush Raina , David Bau , Antonio Torralba , Tamar Rott Shaham

Precise spatial understanding from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs), as their visual representations are predominantly semantic and lack explicit geometric grounding. While…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Chanyoung Gwak , Yoonwoo Jeong , Byungwoo Jeon , Hyunseok Lee , Jinwoo Shin , Minsu Cho

When embodied AI is expanding from traditional object detection and recognition to more advanced tasks of robot manipulation and actuation planning, visual spatial reasoning from the video inputs is necessary to perceive the spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Haoming Wang , Qiyao Xue , Weichen Liu , Wei Gao

3D spatial understanding is essential in real-world applications such as robotics, autonomous vehicles, virtual reality, and medical imaging. Recently, Large Language Models (LLMs), having demonstrated remarkable success across various…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Jirong Zha , Yuxuan Fan , Xiao Yang , Chen Gao , Xinlei Chen

Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yanchun Cheng , Rundong Wang , Xulei Yang , Alok Prakash , Daniela Rus , Marcelo H Ang , ShiJie Li

3D Visual Grounding (3DVG) focuses on locating objects in 3D scenes based on natural language descriptions, serving as a fundamental task for embodied AI and robotics. Recent advances in Multi-modal Large Language Models (MLLMs) have…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Beining Xu , Siting Zhu , Zhao Jin , Junxian Li , Hesheng Wang

This paper presents AlphaSpace, a novel methodology designed to enhance the spatial reasoning capabilities of language models for robotic manipulation in 3D Cartesian space. AlphaSpace employs a hierarchical semantics-based tokenization…

Computation and Language · Computer Science 2025-03-28 Alan Dao , Dinh Bach Vu , Bui Quang Huy

Long-horizon egocentric video presents significant challenges for visual navigation due to viewpoint drift and the absence of persistent geometric context. Although recent vision-language models perform well on image and short-video…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 James Tribble , Hao Wang , Si-En Hong , Chaoyi Zhou , Ashish Bastola , Siyu Huang , Abolfazl Razi

An effective method for combining frozen large language models (LLM) and visual encoders involves a resampler module that creates a `visual prompt' which is provided to the LLM, along with the textual prompt. While this approach has enabled…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Georgios Pantazopoulos , Alessandro Suglia , Oliver Lemon , Arash Eshghi

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but they continue to struggle with spatial understanding. Existing spatial MLLMs often rely on explicit 3D inputs or architecture-specific…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Hunar Batra , Haoqin Tu , Hardy Chen , Yuanze Lin , Cihang Xie , Ronald Clark

Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks,…

Visual reasoning is dominated by end-to-end neural networks scaled to billions of model parameters and training examples. However, even the largest models struggle with compositional reasoning, generalization, fine-grained spatial and…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Aleksandar Stanić , Sergi Caelles , Michael Tschannen

Existing Multimodal Large Language Models (MLLMs) struggle with 3D spatial reasoning, as they fail to construct structured abstractions of the 3D environment depicted in video inputs. To bridge this gap, drawing inspiration from cognitive…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Jiacheng Hua , Yishu Yin , Yuhang Wu , Tai Wang , Yifei Huang , Miao Liu