1 citations · 1 across the 14 of their papers we have counts for
19 papers
MORE: Learning Motion-Oriented Registers for Driving World Models and Planning
Yingdong Gu, Haoyu Wang, Shaocheng Yan +9
By predicting future states, latent world models provide rich self-supervision for end-to-end driving, but often inherit dense features from pretrained visual encoders as their wor…
F SLAM: Turning Feed-Forward Geometry into Persistent Factors for SLAM
Zhisong Xu, Fan Zhu, Jiawei Qian +3
Feed-forward 3D models provide strong multi-view geometric priors, while on- line simultaneous localization and mapping (SLAM) relies mainly on local mea- surements and can accumul…
SSMB: Self-Supervised Local Feature Detection under Motion Blur
Zhenjun Zhao, Fabio Bellavia, Wenting Wang +6
Keypoint detection under motion blur remains a significant challenge, as blur distorts local image structure and degrades the repeatability of feature localization. Existing approa…
MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM
Fan Zhu, Ziyu Chen, Zhenjun Zhao +5
Real-time monocular Simultaneous Localization and Mapping (SLAM) fundamentally suffers from scale ambiguity and a lack of geometric self-correction. While 3D Gaussian Splatting (3D…
ULF-Loc: Unbiased Landmark Feature for Robust Visual Localization with 3D Gaussian Splatting
Yingdong Gu, Shaocheng Yan, Zhenjun Zhao +4
Visual localization is a core technology for augmented reality and autonomous navigation. Recent methods combine the efficient rendering of 3D Gaussian Splatting (3DGS) with featur…
Advances in Global Solvers for 3D Vision
Zhenjun Zhao, Heng Yang, Bangyan Liao +7
Global solvers have emerged as a powerful paradigm for 3D vision, offering certifiable solutions to nonconvex geometric optimization problems traditionally addressed by local or he…
Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning
Jiayao Mai, Bangyan Liao, Zhenjun Zhao +6
The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-findin…
AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction
Jiewen Chan, Zhenjun Zhao, Yu-Lun Liu
Reconstructing dynamic 3D scenes from monocular videos requires simultaneously capturing high-frequency appearance details and temporally continuous motion. Existing methods using…
STG-Avatar: Animatable Human Avatars via Spacetime Gaussian
Guangan Jiang, Tianzi Zhang, Dong Li +4
Realistic animatable human avatars from monocular videos are crucial for advancing human-robot interaction and enhancing immersive virtual experiences. While recent research on 3DG…
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai +6
Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a challenging yet valuable task for immersive and embodied applications. The challenge lies in t…
TurboReg: TurboClique for Robust and Efficient Point Cloud Registration
Shaocheng Yan, Pengcheng Shi, Zhenjun Zhao +4
Robust estimation is essential in correspondence-based Point Cloud Registration (PCR). Existing methods using maximal clique search in compatibility graphs achieve high recall but…
Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World
Bangyan Liao, Zhenjun Zhao, Haoang Li +4
Determining the vanishing points (VPs) in a Manhattan world, as a fundamental task in many 3D vision applications, consists of jointly inferring the line-VP association and locatin…
Surgical Gaussian Surfels: Highly Accurate Real-time Surgical Scene Rendering using Gaussian Surfels
Idris O. Sunmola, Zhenjun Zhao, Samuel Schmidgall +4
Accurate geometric reconstruction of deformable tissues in monocular endoscopic video remains a fundamental challenge in robot-assisted minimally invasive surgery. Although recent…
Image Matching Filtering and Refinement by Planes and Beyond
Fabio Bellavia, Zhenjun Zhao, Luca Morelli +1
This paper provides a consistent and extensive evaluation of state-of-the-art filtering and refinement methods on common image matching pipelines. Unlike previous comparisons, the…
ES-Gaussian: Gaussian Splatting Mapping via Error Space-Based Gaussian Completion
Lu Chen, Yingfu Zeng, Haoang Li +3
Accurate and affordable indoor 3D reconstruction is critical for effective robot navigation and interaction. Traditional LiDAR-based mapping provides high precision but is costly,…
GlobalPointer: Large-Scale Plane Adjustment with Bi-Convex Relaxation
Bangyan Liao, Zhenjun Zhao, Lu Chen +3
Plane adjustment (PA) is crucial for many 3D applications, involving simultaneous pose estimation and plane recovery. Despite recent advancements, it remains a challenging problem…
DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector
Johan Edstedt, Georg Bökman, Zhenjun Zhao
In this paper, we analyze and improve into the recently proposed DeDoDe keypoint detector. We focus our analysis on some key issues. First, we find that DeDoDe keypoints tend to cl…
SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real Images
Junjie Wen, Jinqiang Cui, Zhenjun Zhao +4
Underwater image enhancement (UIE) is vital for high-level vision-related underwater tasks. Although learning-based UIE methods have made remarkable achievements in recent years, i…
BALF: Simple and Efficient Blur Aware Local Feature Detector
Zhenjun Zhao, Yu Zhai, Ben M. Chen +1
Local feature detection is a key ingredient of many image processing and computer vision applications, such as visual odometry and localization. Most existing algorithms focus on f…