English
Related papers

Related papers: SceneFunRI: Reasoning the Invisible for Task-Drive…

200 papers

This thesis introduces "Embodied Spatial Intelligence" to address the challenge of creating robots that can perceive and act in the real world based on natural language instructions. To bridge the gap between Large Language Models (LLMs)…

Robotics · Computer Science 2025-09-03 Jiading Fang

Spatial understanding over continuous visual input is crucial for MLLMs to evolve into general-purpose assistants in physical environments. Yet there is still no comprehensive benchmark that holistically assesses the progress toward this…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Jingli Lin , Runsen Xu , Shaohao Zhu , Sihan Yang , Peizhou Cao , Yunlong Ran , Miao Hu , Chenming Zhu , Yiman Xie , Yilin Long , Wenbo Hu , Dahua Lin , Tai Wang , Jiangmiao Pang

While contemporary Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by a passive, 2D-centric paradigm that severely limits genuine 3D spatial reasoning. To bridge this gap, we introduce Think3D, a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Zaibin Zhang , Yuhan Wu , Lianjie Jia , Yifan Wang , Zhongbo Zhang , Yijiang Li , Binghao Ran , Fuxi Zhang , Zhuohan Sun , Zhenfei Yin , Lijun Wang , Huchuan Lu

Spatial referring is a fundamental capability of embodied robots to interact with the 3D physical world. However, even with the powerful pretrained vision language models (VLMs), recent approaches are still not qualified to accurately…

Although large Vision-Language Models (VLMs) have demonstrated remarkable performance in a wide range of multimodal tasks, their true reasoning capabilities on human IQ tests remain underexplored. To advance research on the fluid…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Tan-Hanh Pham , Phu-Vinh Nguyen , Dang The Hung , Bui Trong Duong , Vu Nguyen Thanh , Chris Ngo , Tri Quang Truong , Truong-Son Hy

Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard…

Computer Vision and Pattern Recognition · Computer Science 2014-11-24 M. Zeeshan Zia , Michael Stark , Konrad Schindler

Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Wenyu Zhang , Wei En Ng , Lixin Ma , Yuwen Wang , Junqi Zhao , Allison Koenecke , Boyang Li , Lu Wang

Detecting AI-generated images with multimodal large language models (MLLMs) has gained increasing attention, due to their rich world knowledge, common-sense reasoning, and potential for explainability. However, naively applying those MLLMs…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Kaiqing Lin , Zhiyuan Yan , Ruoxin Chen , Junyan Ye , Ke-Yue Zhang , Yue Zhou , Peng Jin , Bin Li , Taiping Yao , Shouhong Ding

Humans naturally possess the spatial reasoning ability to form and manipulate images and structures of objects in space. There is an increasing effort to endow Vision-Language Models (VLMs) with similar spatial reasoning capabilities.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Jiahuan Zhang , Shunwen Bai , Tianheng Wang , Kaiwen Guo , Kai Han , Guozheng Rao , Kaicheng Yu

The ability to interpret and comprehend a 3D scene is essential for many vision and robotics systems. In numerous applications, this involves 3D object detection, i.e.~identifying the location and dimensions of objects belonging to a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Olivier Moliner , Viktor Larsson , Kalle Åström

We introduce STSBench, a scenario-based framework to benchmark the holistic understanding of vision-language models (VLMs) for autonomous driving. The framework automatically mines pre-defined traffic scenarios from any dataset using…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Christian Fruhwirth-Reisinger , Dušan Malić , Wei Lin , David Schinagl , Samuel Schulter , Horst Possegger

Currently, utilizing large language models to understand the 3D world is becoming popular. Yet existing 3D-aware LLMs act as black boxes: they output bounding boxes or textual answers without revealing how those decisions are made, and they…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Zhihao Yuan , Shuyi Jiang , Chun-Mei Feng , Yaolun Zhang , Shuguang Cui , Zhen Li , Na Zhao

Vision-Language Models (VLMs) have advanced rapidly in multimodal perception and language understanding, yet it remains unclear whether they can reliably ground language into spatially coherent, plausibly executable actions in 3D digital…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Niyati Rawal , Sushant Ravva , Shah Alam Abir , Saksham Jain , Aman Chadha , Vinija Jain , Suranjana Trivedy , Amitava Das

Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the…

Artificial Intelligence · Computer Science 2025-09-09 Ruixun Liu , Lingyu Kong , Derun Li , Hang Zhao

Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban…

Computer Vision and Pattern Recognition · Computer Science 2025-09-01 Juneyoung Ro , Namwoo Kim , Yoonjin Yoon

Recently spatial-temporal intelligence of Visual-Language Models (VLMs) has attracted much attention due to its importance for autonomous driving, embodied AI and general AI. Existing spatial-temporal benchmarks mainly focus on egocentric…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Qinghongbing Xie , Zhaoyuan Xia , Feng Zhu , Lijun Gong , Ziyue Li , Rui Zhao , Long Zeng

Complex 3D scene understanding has gained increasing attention, with scene encoding strategies playing a crucial role in this success. However, the optimal scene encoding strategies for various scenarios remain unclear, particularly…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Yunze Man , Shuhong Zheng , Zhipeng Bao , Martial Hebert , Liang-Yan Gui , Yu-Xiong Wang

Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Ziyu Zhu , Xilin Wang , Yixuan Li , Zhuofan Zhang , Xiaojian Ma , Yixin Chen , Baoxiong Jia , Wei Liang , Qian Yu , Zhidong Deng , Siyuan Huang , Qing Li

Viewpoint planning is an important task in any application where objects or scenes need to be viewed from different angles to achieve sufficient coverage. The mapping of confined spaces such as shelves is an especially challenging task…

Robotics · Computer Science 2023-07-25 Nils Dengler , Sicong Pan , Vamsi Kalagaturu , Rohit Menon , Murad Dawood , Maren Bennewitz

This technical report presents our solution for the RoboSense Challenge at IROS 2025, which evaluates Vision-Language Models (VLMs) on autonomous driving scene understanding across perception, prediction, planning, and corruption detection…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Aodi Wu , Xubo Luo