87 citations · 137 across the 15 of their papers we have counts for
17 papers
Large Depth Completion Model from Sparse Observations
Zhu Yu, Zhengyi Zhao, Runmin Zhang +7
This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without rely…
Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models
Jiyao Zhang, Mingxu Zhang, Yitong Peng +8
Are current Vision Language Models (VLMs) ready to comprehend and reason about complex embodied interactions in 3D environments? We introduce Embodied3DBench, a robot-centric bench…
Towards Consistent Video Geometry Estimation
Zhu Yu, Jingnan Gao, Runmin Zhang +9
This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built upon a plain transformer arc…
RC-GeoCP: Geometric Consensus for 4D Radar-Camera Collaborative Perception
Xiaokai Bai, Lianqing Zheng, Runwei Guan +3
Collaborative perception (CP) extends sensing range through feature sharing, but most systems remain LiDAR-centric. Camera and 4D radar sensing combines dense semantics with lower-…
Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
Runmin Zhang, Jialiang Wang, Si-Yuan Cao +4
This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Un…
EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration
Haokai Zhu, Bo Qu, Si-Yuan Cao +4
Previous deep image registration methods that employ single homography, multi-grid homography, or thin-plate spline often struggle with real scenes containing depth disparities due…
Recurrent Cross-View Object Geo-Localization
Xiaohan Zhang, Si-Yuan Cao, Xiaokai Bai +7
Cross-view object geo-localization (CVOGL) aims to determine the location of a specific object in high-resolution satellite imagery given a query image with a point prompt. Existin…
RestorerID: Towards Tuning-Free Face Restoration with ID Preservation
Jiacheng Ying, Mushui Liu, Zhe Wu +7
Blind face restoration has made great progress in producing high-quality and lifelike images. Yet it remains challenging to preserve the ID information especially when the degradat…
Language Driven Occupancy Prediction
Zhu Yu, Bowen Pang, Lizhe Liu +7
We introduce LOcc, an effective and generalizable framework for open-vocabulary occupancy (OVO) prediction. Previous approaches typically supervise the networks through coarse voxe…
SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization
Junchen Yu, Si-Yuan Cao, Runmin Zhang +5
We propose a novel unsupervised cross-modal homography estimation learning framework, named Split Supervised Homography estimation Network (SSHNet). SSHNet reformulates the unsuper…
SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning
Runmin Zhang, Jun Ma, Si-Yuan Cao +5
We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namel…
Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection
Xue Zhang, Si-Yuan Cao, Fang Wang +5
Most recent multispectral object detectors employ a two-branch structure to extract features from RGB and thermal images. While the two-branch structure achieves better performance…
Context and Geometry Aware Voxel Transformer for Semantic Scene Completion
Zhu Yu, Runmin Zhang, Jiacheng Ying +5
Vision-based Semantic Scene Completion (SSC) has gained much attention due to its widespread applications in various 3D perception tasks. Existing sparse-to-dense approaches typica…
SGDFormer: One-stage Transformer-based Architecture for Cross-Spectral Stereo Image Guided Denoising
Runmin Zhang, Zhu Yu, Zehua Sheng +6
Cross-spectral image guided denoising has shown its great potential in recovering clean images with rich details, such as using the near-infrared image to guide the denoising proce…
TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection
Xue Zhang, Xiaohan Zhang, Jiangtao Wang +5
Pedestrian detection plays a critical role in computer vision as it contributes to ensuring traffic safety. Existing methods that rely solely on RGB images suffer from performance…
I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections
Shuhang Zheng, Yixuan Li, Zhu Yu +8
Place recognition is an important technique for autonomous cars to achieve full autonomy since it can provide an initial guess to online localization algorithms. Although current m…
BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images
Lun Luo, Shuhang Zheng, Yixuan Li +4
Place recognition is a key module for long-term SLAM systems. Current LiDAR-based place recognition methods usually use representations of point clouds such as unordered points or…