English
Related papers

Related papers: Towards Scalable Spatial Intelligence via 2D-to-3D…

200 papers

This paper introduces a pipeline to parametrically sample and render multi-task vision datasets from comprehensive 3D scans from the real world. Changing the sampling parameters allows one to "steer" the generated datasets to emphasize…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Ainaz Eftekhar , Alexander Sax , Roman Bachmann , Jitendra Malik , Amir Zamir

Data-driven developments in lensless imaging, such as machine learning-based reconstruction algorithms, require large datasets. In this work, we introduce a data acquisition pipeline that can capture from multiple lensless imaging systems…

Image and Video Processing · Electrical Eng. & Systems 2026-02-03 Clara S. Hung , Leyla A. Kabuli , Vasilisa Ponomarenko , Laura Waller

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Yingping Liang , Ying Fu , Yutao Hu , Wenqi Shao , Jiaming Liu , Debing Zhang

Given the prominence of current 3D sensors, a fine-grained analysis on the basic point cloud data is worthy of further investigation. Particularly, real point cloud scenes can intuitively capture complex surroundings in the real world, but…

Computer Vision and Pattern Recognition · Computer Science 2021-04-14 Shi Qiu , Saeed Anwar , Nick Barnes

Over the past year, the development of large language models (LLMs) has brought spatial intelligence into focus, with much attention on vision-based embodied intelligence. However, spatial intelligence spans a broader range of disciplines…

We propose SpatialLLM, a novel approach advancing spatial intelligence tasks in complex urban scenes. Unlike previous methods requiring geographic analysis tools or domain expertise, SpatialLLM is a unified language model directly…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Jiabin Chen , Haiping Wang , Jinpeng Li , Yuan Liu , Zhen Dong , Bisheng Yang

Precise robot manipulations require rich spatial information in imitation learning. Image-based policies model object positions from fixed cameras, which are sensitive to camera view changes. Policies utilizing 3D point clouds usually…

Robotics · Computer Science 2024-09-11 Chenxi Wang , Hongjie Fang , Hao-Shu Fang , Cewu Lu

Embodied intelligence, a grand challenge in artificial intelligence, is fundamentally constrained by the limited spatial understanding and reasoning capabilities of current models. Prevailing efforts to address this through enhancing…

Artificial Intelligence · Computer Science 2025-12-19 Zhi Helu , Huang Jingjing , Xu Wang , Xu Yangbin , Zhang Wanyue , Jiang Baoyang , Deng Shirui , Zhu Liang , Li Fangfang , Zhao Tiejun , Lin Yankai , Yao Yuan

Holistic understanding of urban scenes based on RGB images is a challenging yet important problem. It encompasses understanding both the geometry and appearance to enable novel view synthesis, parsing semantic labels, and tracking moving…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Hongyu Zhou , Jiahao Shao , Lu Xu , Dongfeng Bai , Weichao Qiu , Bingbing Liu , Yue Wang , Andreas Geiger , Yiyi Liao

Recent advancements in photo-realistic novel view synthesis have been significantly driven by Gaussian Splatting (3DGS). Nevertheless, the explicit nature of 3DGS data entails considerable storage requirements, highlighting a pressing need…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Minye Wu , Tinne Tuytelaars

This paper addresses the high demand in advanced intelligent robot navigation for a more holistic understanding of spatial environments, by introducing a novel system that harnesses the capabilities of Large Language Models (LLMs) to…

Robotics · Computer Science 2025-03-20 Yao Cheng , Zhe Han , Fengyang Jiang , Huaizhen Wang , Fengyu Zhou , Qingshan Yin , Lei Wei

The image enhancement methods based on 3D lookup tables (3D LUTs) efficiently reduce both model size and runtime by interpolating pre-calculated values at the vertices. However, the 3D LUT methods have a limitation due to their lack of…

Image and Video Processing · Electrical Eng. & Systems 2025-08-25 Wontae Kim , Keuntek Lee , Nam Ik Cho

Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Andrew Caunes , Thierry Chateau , Vincent Frémont

This paper presents an automated pipeline for processing multi-view satellite images to 3D digital surface models (DSM). The proposed pipeline performs automated geo-referencing and generates high-quality densely matched point clouds. In…

Computer Vision and Pattern Recognition · Computer Science 2019-10-08 Rongjun Qin

Open-vocabulary panoptic reconstruction is essential for advanced robotics perception and simulation. However, existing methods based on 3D Gaussian Splatting (3DGS) often struggle to simultaneously achieve geometric accuracy, coherent…

Robotics · Computer Science 2026-04-14 Xuan Yu , Yuxuan Xie , Changjian Jiang , Shichao Zhai , Rong Xiong , Yu Zhang , Yue Wang

RGB-D cameras supply rich and dense visual and spatial information for various robotics tasks such as scene understanding, map reconstruction, and localization. Integrating depth and visual information can aid robots in localization and…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Ali Tourani , Saad Ejaz , Hriday Bavle , Jose Luis Sanchez-Lopez , Holger Voos

Humans naturally understand 3D spatial relationships, enabling complex reasoning like predicting collisions of vehicles from different directions. Current large multimodal models (LMMs), however, lack of this capability of 3D spatial…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Wufei Ma , Luoxin Ye , Celso M de Melo , Jieneng Chen , Alan Yuille

Data augmentation has been highly effective in narrowing the data gap and reducing the cost for human annotation, especially for tasks where ground truth labels are difficult and expensive to acquire. In face recognition, large pose and…

Computer Vision and Pattern Recognition · Computer Science 2020-10-07 Yifan Xing , Yuanjun Xiong , Wei Xia

Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language…

Robotics · Computer Science 2025-11-03 Simindokht Jahangard , Mehrzad Mohammadi , Abhinav Dhall , Hamid Rezatofighi

In recent years, we have witnessed the growing interest from academia and industry in applying data science technologies to analyze large amounts of data. In this process, a myriad of artifacts (datasets, pipeline scripts, etc.) are…