中文
相关论文

相关论文: PanoWorld: Towards Spatial Supersensing in 360$^\c…

200 篇论文

Multimodal Large Language Models (MLLMs) require comprehensive visual inputs to achieve dense understanding of the physical world. While existing MLLMs demonstrate impressive world understanding capabilities through limited field-of-view…

计算机视觉与模式识别 · 计算机科学 2025-06-18 Yikang Zhou , Tao Zhang , Dizhe Zhang , Shunping Ji , Xiangtai Li , Lu Qi

Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence. Pure 2D generators produce appealing single panoramas but re-imagine geometry and…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Jinrang Jia , Zhenjia Li , Yijiang Hu , Yifeng Shi

In panorama understanding, the widely used equirectangular projection (ERP) entails boundary discontinuity and spatial distortion. It severely deteriorates the conventional CNNs and vision Transformers on panoramas. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2023-08-29 Zhixin Ling , Zhen Xing , Xiangdong Zhou , Manliang Cao , Guichun Zhou

360 panoramic images are increasingly used in virtual reality, autonomous driving, and robotics for holistic scene understanding. However, current Vision-Language Models (VLMs) struggle with 3D spatial reasoning on Equirectangular…

计算机视觉与模式识别 · 计算机科学 2026-02-26 Zekai Lin , Xu Zheng

3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reasoning. Traditional supervised models leverage explicit 3D geometry but exhibit limited…

计算机视觉与模式识别 · 计算机科学 2025-12-25 Seongmin Jung , Seongho Choi , Gunwoo Jeon , Minsu Cho , Jongwoo Lim

Understanding perspective is fundamental to human visual perception, yet the extent to which multimodal large language models (MLLMs) internalize perspective geometry remains unclear. We introduce MMPerspective, the first benchmark…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Yolo Y. Tang , Pinxin Liu , Zhangyun Tan , Mingqian Feng , Rui Mao , Chao Huang , Jing Bi , Yunzhong Xiao , Susan Liang , Hang Hua , Ali Vosoughi , Luchuan Song , Zeliang Zhang , Chenliang Xu

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Diankun Wu , Fangfu Liu , Yi-Hsin Hung , Yueqi Duan

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

人工智能 · 计算机科学 2025-12-03 Qiyao Xue , Weichen Liu , Shiqi Wang , Haoming Wang , Yuyang Wu , Wei Gao

Current Large Multimodal Models (LMMs) in Earth Observation typically neglect the critical "vertical" dimension, limiting their reasoning capabilities in complex remote sensing geometries and disaster scenarios where physical spatial…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Xuran Hu , Zhitong Xiong , Zhongcheng Hong , Yifang Ban , Xiaoxiang Zhu , Wufan Zhao

Generating a complete and explorable 360-degree visual world enables a wide range of downstream applications. While prior works have advanced the field, they remain constrained by either narrow field-of-view limitations, which hinder the…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Yuyang Yin , HaoXiang Guo , Fangfu Liu , Mengyu Wang , Hanwen Liang , Eric Li , Yikai Wang , Xiaojie Jin , Yao Zhao , Yunchao Wei

Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints. We study this challenge as Perspective-Conditioned Spatial Reasoning (PCSR) in 360-degree…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Yuangong Chen , Wai Keung Wong , Jiaxing Li , Ioannis Patras , Xu Zheng

Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Wei Wang , Yuqian Yuan , Tianwei Lin , Wenqiao Zhang , Siliang Tang , Jun Xiao , Yueting Zhuang

Advancing towards artificial superintelligence requires rich and intelligent perceptual capabilities. A critical frontier in this pursuit is overcoming the limited spatial understanding of Multimodal Large Language Models (MLLMs), where…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Ruiheng Liu , Haihong Hao , Mingfei Han , Xin Gu , Kecheng Zhang , Changlin Li , Xiaojun Chang

Zero-shot object navigation (ZSON) in unseen environments remains a challenging problem for household robots, requiring strong perceptual understanding and decision-making capabilities. While recent methods leverage metric maps and Large…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Qunchao Jin , Yilin Wu , Changhao Chen

Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical…

计算机视觉与模式识别 · 计算机科学 2026-02-19 Zelin Xu , Yupu Zhang , Saugat Adhikari , Saiful Islam , Tingsong Xiao , Zibo Liu , Shigang Chen , Da Yan , Zhe Jiang

We present PanoWorld, a panoramic video world model that generates geometry-consistent 360$\degree$ video from a single image and a caption. Existing panoramic video methods optimize primarily for visual realism and do not explicitly…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Le Jiang , Xiangyu Bai , Bishoy Galoaa , Shayda Moezzi , Caleb James Lee , Tooba Imtiaz , Edmund Yeh , Jennifer Dy , Yanzhi Wang , Sarah Ostadabbas

Recent multimodal large language models (MLLMs) have made remarkable progress in visual understanding and language-based reasoning, yet they lack a persistent world-centered representation for spatially consistent reasoning in 3D…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Bo Gu , Zhikang Zhang , Zizhuang Wei , Zhenyuan Chen , Lingyun Li , Zhuoyi Song

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Jiahua Chen , Qihong Tang , Weinong Wang , Qi Fan

Multi-view understanding, the ability to reconcile visual information across diverse viewpoints for effective navigation, manipulation, and 3D scene comprehension, is a fundamental challenge in Multi-Modal Large Language Models (MLLMs) to…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Chun-Hsiao Yeh , Chenyu Wang , Shengbang Tong , Ta-Ying Cheng , Ruoyu Wang , Tianzhe Chu , Yuexiang Zhai , Yubei Chen , Shenghua Gao , Yi Ma

Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content, but significant challenges persist in tasks requiring cross-viewpoint understanding and spatial reasoning. We…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Dingming Li , Hongxing Li , Zixuan Wang , Yuchen Yan , Hang Zhang , Siqi Chen , Guiyang Hou , Shengpei Jiang , Wenqi Zhang , Yongliang Shen , Weiming Lu , Yueting Zhuang
‹ 上一页 1 2 3 10 下一页 ›