3D 视觉

ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields

Corinne Stucker, Bingxin Ke, Yuanwen Yue, Shengyu Huang, Iro Armeni, Konrad Schindler

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments Accepted for publication in the International Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (camera-ready version including keywords + supplementary material)

Journal ref ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2022, 193-201, 2022

ScanQA: 3D Question Answering for Spatial Scene Understanding

Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, Motoaki Kawanabe

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.CV

Comments CVPR2022. The first three authors are equally contributed. Project page: https://github.com/ATR-DBI/ScanQA

Towards 3D Scene Understanding by Referring Synthetic Models

Runnan Chen, Xinge Zhu, Nenglun Chen, Dawei Wang, Wei Li, Yuexin Ma, Ruigang Yang, Wenping Wang

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine

Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Weiming Wang, Cewu Lu

专题命中 空间理解 ：3D vision(abstract)；分类 cs.CV

Comments Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence; To appear in upcoming issues

A Simulation-based End-to-End Learning Framework for Evidential Occupancy Grid Mapping

Raphael van Kempen, Bastian Lampe, Timo Woopen, Lutz Eckstein

专题命中 空间理解 ：point cloud(abstract)；分类 cs.RO

Comments Accepted to be published as part of the 2021 IEEE Intelligent Vehicles Symposium (IV), Nagoya, Japan, July 11-15, 2021

Teaching Math with the help of Virtual Reality

Marco Simonetti, Damiano Perri, Natale Amato, Osvaldo Gervasi

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.GR

Comments International Conference on Computational Science and Its Applications, ICCSA 2020

Journal ref LNCS, volume 12255, 2020

Multi-View Fusion for Multi-Level Robotic Scene Understanding

Yunzhi Lin, Jonathan Tremblay, Stephen Tyree, Patricio A. Vela, Stan Birchfield

专题命中 空间理解 ：point cloud(abstract)；分类 cs.RO

Comments Presented at IROS 2021. Video is at https://youtu.be/FuqMxuODGlw

Weakly Supervised Relative Spatial Reasoning for Visual Question Answering

Pratyay Banerjee, Tejas Gokhale, Yezhou Yang, Chitta Baral

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.CV

Comments Accepted to ICCV 2021. PaperId : ICCV2021-10857 Copyright transferred to IEEE ICCV. DOI will be updated later

SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks

Jiapeng Tang, Jiabao Lei, Dan Xu, Feiying Ma, Kui Jia, Lei Zhang

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments ICCV2021 Oral Representation; 16 pages; 14 figures; 5 tables

Sharing Cognition: Human Gesture and Natural Language Grounding Based Planning and Navigation for Indoor Robots

Gourav Kumar, Soumyadip Maity, Ruddra dev Roychoudhury, Brojeshwar Bhowmick

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.RO

Real-time Semantic 3D Dense Occupancy Mapping with Efficient Free Space Representations

Yuanxin Zhong, Huei Peng

专题命中 空间理解 ：point cloud(abstract)；分类 cs.RO

Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts

Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments CVPR 2021

3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding

Shengheng Deng, Xun Xu, Chaozheng Wu, Ke Chen, Kui Jia

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments CVPR2021 accepted paper

Bidirectional Projection Network for Cross Dimension Scene Understanding

Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments CVPR 2021 (Oral)

Journal ref CVPR 2021

RadVR: A 6DOF Virtual Reality Daylighting Analysis Tool

Mohammad Keshavarzi, Luisa Caldas, Luis Santos

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.GR

Comments Accepted to Automation in Construction

P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding

Yunze Liu, Li Yi, Shanghang Zhang, Qingnan Fan, Thomas Funkhouser, Hao Dong

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Exploring Deep 3D Spatial Encodings for Large-Scale 3D Scene Understanding

Saqib Ali Khan, Yilei Shi, Muhammad Shahzad, Xiao Xiang Zhu

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments Submitted to IEEE Geoscience and Remote Sensing Letters (GRSL) Journal

Learning to Predict the 3D Layout of a Scene

Jihao Andreas Lin, Jakob Brünker, Daniel Fährmann

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Acquiring Common Sense Spatial Knowledge through Implicit Spatial Templates

Guillem Collell, Luc Van Gool, Marie-Francine Moens

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.CV

Comments To appear at AAAI 2018 Conference

Visual Question Answering on 360° Images

Shih-Han Chou, Wei-Lun Chao, Wei-Sheng Lai, Min Sun, Ming-Hsuan Yang

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.CV

Comments Accepted to WACV 2020

Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial Scans

Cheng Lin, Changjian Li, Wenping Wang

专题命中 空间理解 ：3D reconstruction(abstract)；分类 cs.CV

Comments Published at ICCV 2019. Previously on arxiv as "Floorplan Priors for Joint Camera Pose and Room Layout Estimation"

Multi-view PointNet for 3D Scene Understanding

Maximilian Jaritz, Jiayuan Gu, Hao Su

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments Geometry Meets Deep Learning Workshop, ICCV 2019

Deep Reason: A Strong Baseline for Real-World Visual Reasoning

Chenfei Wu, Yanzhao Zhou, Gen Li, Nan Duan, Duyu Tang, Xiaojie Wang

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.CV

Comments CVPR 2019 Visual Question Answering and Dialog Workshop

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction

Yifei Shi, Angel Xuan Chang, Zhelun Wu, Manolis Savva, Kai Xu

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments CVPR 2019

Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey

Muzammal Naseer, Salman H Khan, Fatih Porikli

专题命中 空间理解 ：3D reconstruction(abstract)；分类 cs.CV

Comments IEEE Access

Journal ref Year: DECEMBER 2019, Volume: 7, Issue:1, Page(s): 1859-1887,

Spatial Knowledge Distillation to aid Visual Reasoning

Somak Aditya, Rudra Saha, Yezhou Yang, Chitta Baral

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.CV

Comments Equal contribution by first two authors. Accepted in WACV 2019

Multiview Based 3D Scene Understanding On Partial Point Sets

Ye Zhu, Sven Ewan Shepstone, Pablo Martínez-Nuevo, Miklas Strøm Kristoffersen, Fabien Moutarde, Zhuang Fu

专题命中 空间理解 ：point cloud(abstract)；分类 cs.CV

Comments This paper has been submitted to IEEE Transactions on Neural Networks and Learning Systems

LMM Modality Transfer: A Pre-requisite for Autonomous GIS Agents

多模态大模型模态迁移：自主地理信息系统智能体的先决条件

Ivan Majic, Zexian Huang, Franziska Hübl, Krzysztof Janowicz, Meilin Shi, Mina Karimi, Zilong Liu, Alexandra Fortacz-Lazan

机构 * Graz University of Technology（格拉茨工业大学） ； University of Vienna（维也纳大学） ； University of Liverpool（利物浦大学） 纠错

专题命中 空间理解 ：spatial understanding(abstract)

AI总结 本文针对自主GIS智能体的先决条件，提出LMM模态迁移任务，发现现有LMM在图像与文本模态间传递空间信息的能力不足，需加强多模态对齐以实现地理空间理解。

Beyond Static Forecasting: Unleashing the Power of World Models for Mobile Traffic Extrapolation

超越静态预测：利用世界模型进行移动交通外推

Xiaoqian Qi, Haoye Chai, Yue Wang, Yong Li

专题命中 空间理解 ：spatial understanding(abstract)

AI总结 本文提出MobiWM世界模型，用于移动网络中的移动交通外推，通过融合多模态环境上下文和编码动作，提升空间理解，实验表明其在所有评估场景中均取得最佳分布保真度。

CrossAtlas: Evaluating Projection Techniques for Spatial Referencing in Cross-Reality Collaboration

CrossAtlas：评估跨现实协作中空间参考的投影技术

Haoyang Yang, Chenyang Zhang, Elliott H. Faa, Weijian Liu, Lily Seika Chisholm, Benjamin Lee, David Saffo, Feiyu Lu, Blair MacIntyre, Yalong Yang

专题命中 空间理解 ：spatial understanding(abstract)

AI总结 CrossAtlas是整合多种投影技术的PC-VR协作平台，经24组双人受控研究发现，球形投影变体在空间参考任务中表现优于平面投影，可提升跨现实协作效果。

Comments 11 pages, 8 figures, Accepted to IEEE ISMAR 2026 (TVCG journal track)