24 citations · 56 across the 25 of their papers we have counts for
25 papers
CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation
Jingyu Hu, Weilong Yan, Zhengzhe Liu +4
This paper presents a latent-space 3D shape editing framework built upon a coupled neural shape (CNS) representation and a neural feature volume optimization. This work extends CNS…
CamFlow+: Hybrid Motion Bases for 2D Camera Motion Estimation with Stabilization Applications
Haipeng Li, Zhen Liu, Zhanglei Yang +6
Estimating 2D camera motion is fundamental to computer vision and computational photography. Existing homography-based methods work well for planar scenes or pure rotation, but str…
LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency
Weilong Yan, Haipeng Li, Hao Xu +4
This paper introduces LaS-Comp, a zero-shot and category-agnostic approach that leverages the rich geometric priors of 3D foundation models to enable 3D shape completion across div…
Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation
Chongyang Xu, Haipeng Li, Shen Cheng +4
Bimanual manipulation requires policies that can reason about 3D geometry, anticipate how it evolves under action, and generate smooth, coordinated motions. However, existing metho…
HeRO: Hierarchical 3D Semantic Representation for Pose-aware Object Manipulation
Chongyang Xu, Shen Cheng, Haipeng Li +3
Imitation learning for robotic manipulation has progressed from 2D image policies to 3D representations that explicitly encode geometry. Yet purely geometric policies often lack ex…
PEGAsus: 3D Personalization of Geometry and Appearance
Jingyu Hu, Bin Hu, Ka-Hei Hui +4
We present PEGAsus, a new framework capable of generating Personalized 3D shapes by learning shape concepts at both Geometry and Appearance levels. First, we formulate 3D shape per…
Hierarchical Neural Semantic Representation for 3D Semantic Correspondence
Keyu Du, Jingyu Hu, Haipeng Li +4
This paper presents a new approach to estimate accurate and robust 3D semantic correspondence with the hierarchical neural semantic representation. Our work has three key contribut…
Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising
Shen Cheng, Haipeng Li, Haibin Huang +2
In this work, we present Blind-Spot Guided Diffusion, a novel self-supervised framework for real-world image denoising. Our approach addresses two major challenges: the limitations…
Estimating 2D Camera Motion with Hybrid Motion Basis
Haipeng Li, Tianhao Zhou, Zhanglei Yang +6
Estimating 2D camera motion is a fundamental computer vision task that models the projection of 3D camera movements onto the 2D image plane. Current methods rely on either homograp…
StableMotion: One-Step Motion Estimation with Diffusion Prior
Ziyi Wang, Haipeng Li, Lin Sui +5
We present StableMotion, a novel framework that leverages geometric and content priors from pretrained large-scale image diffusion models for motion estimation in single-image rect…
Coding-Prior Guided Diffusion Network for Video Deblurring
Yike Liu, Jianhui Zhang, Haipeng Li +2
While recent video deblurring methods have advanced significantly, they often overlook two valuable prior information: (1) motion vectors (MVs) and coding residuals (CRs) from vide…
CodingHomo: Bootstrapping Deep Homography With Video Coding
Yike Liu, Haipeng Li, Shuaicheng Liu +1
Homography estimation is a fundamental task in computer vision with applications in diverse fields. Recent advances in deep learning have improved homography estimation, particular…
Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors
Weilong Yan, Ming Li, Haipeng Li +2
Self-supervised depth estimation from monocular cameras in diverse outdoor conditions, such as daytime, rain, and nighttime, is challenging due to the difficulty of learning univer…
HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions
Keyu Du, Hao Xu, Haipeng Li +3
Scene-level point cloud registration is very challenging when considering dynamic foregrounds. Existing indoor datasets mostly assume rigid motions, so the trained models cannot ro…
PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training
Suyi Chen, Hao Xu, Haipeng Li +5
Data plays a crucial role in training learning-based methods for 3D point cloud registration. However, the real-world dataset is expensive to build, while rendering-based synthetic…
Single Image Rolling Shutter Removal with Diffusion Models
Zhanglei Yang, Haipeng Li, Mingbo Hong +3
We present RS-Diffusion, the first Diffusion Models-based method for single-frame Rolling Shutter (RS) correction. RS artifacts compromise visual quality of frames due to the row-w…
RecDiffusion: Rectangling for Image Stitching with Diffusion Models
Tianhao Zhou, Haipeng Li, Ziyi Wang +5
Image stitching from different captures often results in non-rectangular boundaries, which is often considered unappealing. To solve non-rectangular boundaries, current solutions i…
HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions
Hao Xu, Haipeng Li, Yinqiao Wang +2
Reconstructing 3D hand mesh robustly from a single image is very challenging, due to the lack of diversity in existing real-world datasets. While data synthesis helps relieve the i…
Supervised Homography Learning with Realistic Dataset Generation
Hai Jiang, Haipeng Li, Songchen Han +3
In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised…
Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions
Haipeng Li, Dingrui Liu, Yu Zeng +5
Accurate segmentation of lesions is crucial for diagnosis and treatment of early esophageal cancer (EEC). However, neither traditional nor deep learning-based methods up to today c…
GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning
Haipeng Li, Kunming Luo, Bing Zeng +1
Existing homography and optical flow methods are erroneous in challenging scenes, such as fog, rain, night, and snow because the basic assumptions such as brightness and gradient c…
DAS: Neural Architecture Search via Distinguishing Activation Score
Yuqiao Liu, Haipeng Li, Yanan Sun +1
Neural Architecture Search (NAS) is an automatic technique that can search for well-performed architectures for a specific task. Although NAS surpasses human-designed architecture…
Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint
Hai Jiang, Haipeng Li, Yuhang Lu +2
Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field. To address it, we propose a progressive estimation strate…
GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
Haipeng Li, Kunming Luo, Shuaicheng Liu
Existing optical flow methods are erroneous in challenging scenes, such as fog, rain, and night because the basic optical flow assumptions such as brightness and gradient constancy…