Spatial AI Lab · Yujiao Shi

Publications

Google Scholar ↗

2026

Overview of Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring

ECCV · 2026 · Award Candidate

Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring

Taeho Kang, Nairan Zhang, Yelin Kim, Yujiao Shi, Youngki Lee

Estimating camera orientation across ground and aerial views under location uncertainty.

Overview of Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images

NeurIPS · 2026

Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images

Qiwei Wang, Zhongyao Tuo, Xianghui Ze, Yujiao Shi *

Cross3R connects satellite, drone, and ground observations through joint 3D reconstruction and camera pose estimation.

Overview of VGA: Empowering Aerial-Ground Localization by Visual Geometry Alignment

CVPR · 2026

VGA: Empowering Aerial-Ground Localization by Visual Geometry Alignment

Tao Jun Lin, Yujiao Shi, Hongdong Li

Overview of PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery

CVPR · 2026

PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery

Yijing Guo, Mengjun Chao, Luo Wang, Tianyang Zhao, Haizhao Dai, Yingliang Zhang, Jingyi Yu, Yujiao Shi *

Joint camera pose, depth, and point-cloud prediction from 360° imagery, with the PanoCity dataset.

Overview of AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis

CVPR · 2026

AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis

Xiaofei Wu, Yi Zhang, Yumeng Liu, Yuexin Ma, Yujiao Shi, Xuming He

Generating human grasps conditioned on object geometry and interaction instructions.

Overview of CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis

ICLR · 2026

CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis

Qiwei Wang, Xianghui Ze, Jingyi Yu, Yujiao Shi *

A panoramic scene representation for novel view synthesis from single or sparse input panoramas.

Overview of SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery

ICLR · 2026

SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery

Xianghui Ze, Beiyi Zhu, Zhenbo Song, Jianfeng Lu, Yujiao Shi *

Generating geometrically consistent ground-level panoramas from a satellite image and a camera trajectory.

2025

Overview of CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians

SIGGRAPH Asia · 2025

CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians

Weihang Liu, Yuhui Zhong, Yuke Li, Xi Chen, Jiadi Cui, Honglong Zhang, Lan Xu, Xin Lou, Yujiao Shi, Jingyi Yu, Yingliang Zhang

Combining building geometry and Gaussian primitives for efficient urban scene rendering.

Overview of GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization

ICCV · 2025

GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization

Shaowen Tong, Zimin Xia, Alexandre Alahi, Xuming He, Yujiao Shi *

Learning cross-view localization with coarse supervision through geometry-guided self-distillation.

Overview of DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarios

IEEE Robotics and Automation Letters · 2025

DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarios

Xiangting Meng, Jiaqi Yang, Mingshu Chen, Chenxin Yan, Yujiao Shi, Wenchao Ding, Laurent Kneip

Overview of BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization

NeurIPS · 2025 · Spotlight

BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization

Qiwei Wang, Shaoxun Wu, and Yujiao Shi *

Overview of Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control

ICLR, 2025

Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control

Xianghui Ze, Zhenbo Song, Qiwei Wang, Jianfeng Lu, and Yujiao Shi *

Overview of FastGrasp: Efficient Grasp Synthesis with Diffusion

3DV, 2025

FastGrasp: Efficient Grasp Synthesis with Diffusion

Xiaofei Wu, Tao Liu, Caoji Li, Yuexin Ma, Yujiao Shi *, and Xuming He*

Overview of Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis

3DV · 2025

Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis

Tao Jun Lin, Wenqing Wang, Yujiao Shi , Akhil Perincherry, Ankit Vora, and Hongdong Li

Earlier publications (2024 and before)

2024

Overview of LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives

ACM Transactions on Graphics · 2024

LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives

Jiadi Cui, Junming Cao, Fuqiang Zhao, Zhipeng He, Yifan Chen, Yuhui Zhong, Lan Xu, Yujiao Shi *, Yingliang Zhang *, Jingyi Yu *

Overview of Weakly-supervised camera localization by ground-to-satellite image registration

ECCV · 2024

Weakly-supervised camera localization by ground-to-satellite image registration

Yujiao Shi, Hongdong Li, Akhil Perincherry, Ankit Vora

Overview of Adapting fine-grained cross-view localization to areas without fine ground truth

ECCV · 2024

Adapting fine-grained cross-view localization to areas without fine ground truth

Zimin Xia, Yujiao Shi , Hongdong Li, and Julian FP Kooij

2023

Overview of Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer

ICCV, 2023

Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer

Yujiao Shi , Fei Wu, Akhil Perincherry, Ankit Vora, and Hongdong Li

2022

Overview of CVLNet: Cross-View Feature Correspondence Learning for Video-based Camera Localization

ACCV, 2022

CVLNet: Cross-View Feature Correspondence Learning for Video-based Camera Localization

Yujiao Shi , Xin Yu, Shan Wang, and Hongdong Li

Overview of Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image

CVPR, 2022

Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image

Yujiao Shi , Hongdong Li

Overview of Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching

TPAMI, 2022

Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching

Yujiao Shi , Xin Yu, Liu Liu, Dylan Campbell, Piotr Koniusz, and Hongdong Li

Overview of Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery

TPAMI, 2022

Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery

Yujiao Shi , Dylan Campbell, Xin Yu, and Hongdong Li

2021

Overview of Self-Supervised Visibility Learning for Novel View Synthesis

CVPR, 2021

Self-Supervised Visibility Learning for Novel View Synthesis

Yujiao Shi , Hongdong Li, and Xin Yu

2020

Overview of Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching

CVPR, 2020

Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching

Yujiao Shi , Xin Yu, Dylan Campbell, and Hongdong Li

Overview of Optimal Feature Transport for Cross-View Image Geo-Localization

AAAI, 2020

Optimal Feature Transport for Cross-View Image Geo-Localization

Yujiao Shi , Xin Yu, Liu Liu, Tong Zhang, and Hongdong Li

2019

Overview of Spatial-Aware Feature Aggregation for Cross-View Image based Geo-Localization

NeurIPS, 2019

Spatial-Aware Feature Aggregation for Cross-View Image based Geo-Localization

Yujiao Shi , Liu Liu, Xin Yu, and Hongdong Li