1 citations · 1 across the 18 of their papers we have counts for
20 papers
Fetch My Beer: Synthetic-to-real Hierarchical Policy for Smooth Pick-and-place
Yingyue Li, Chenyangguang Zhang, Ruida Zhang +3
Many real-world robotic applications require dynamically sensitive manipulation, where success depends not only on reaching a target state but on maintaining stable object dynamics…
3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints
Ziqin Huang, Yingyue Li, Chenyangguang Zhang +6
Intermediate representations are key to bridging the modality gap between generalizable manipulation policies and large-scale pretrained vision-language models (VLMs). Among these,…
Functional-SLAM: Interaction-Aware Mapping with Online Functional Scene Graphs
Xinggang Hu, Chenyangguang Zhang, Zihan Zhu +3
Existing SLAM systems lack modeling of the functional relations required for fine-grained robotic interaction. Functional 3D scene graphs can represent relations between objects an…
Surfsvr: 2D Surface Priors as 3D Geometric Regularizers for Sparse Voxel Reconstruction
Yan Di, Chengxi Li, Yaoxing Wang +7
Sparse voxel reconstruction offers an efficient representation for high-fidelity 3D modeling, yet its geometry is commonly optimized from local photometric evidence and discrete vi…
Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces
Xinggang Hu, Chenyangguang Zhang, Alexandros Delitzas +4
Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes, interactive elements, and fun…
HINT: Hierarchical Interaction Modeling for Autoregressive Multi-Human Motion Generation
Mengge Liu, Yan Di, Gu Wang +4
Text-driven multi-human motion generation with complex interactions remains a challenging problem. Despite progress in performance, existing offline methods that generate fixed-len…
Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces
Chenyangguang Zhang, Alexandros Delitzas, Fangjinhua Wang +4
We introduce the task of predicting functional 3D scene graphs for real-world indoor environments from posed RGB-D images. Unlike traditional 3D scene graphs that focus on spatial…
GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation
Zinqin Huang, Gu Wang, Chenyangguang Zhang +3
Recent advances in RGBD-based category-level object pose estimation have been limited by their reliance on precise depth information, restricting their broader applicability. In re…
Street Gaussians without 3D Object Tracker
Ruida Zhang, Chengxi Li, Chenyangguang Zhang +5
Realistic scene reconstruction in driving scenarios poses significant challenges due to fast-moving objects. Most existing methods rely on labor-intensive manual labeling of object…
GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024
Xingyu Liu, Gu Wang, Chengxi Li +4
We present GFreeDet, an unseen object detection approach that leverages Gaussian splatting and vision Foundation models under model-free setting. Unlike existing methods that rely…
UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
Xingyu Liu, Gu Wang, Ruida Zhang +3
Unseen object pose estimation methods often rely on CAD models or multiple reference views, making the onboarding stage costly. To simplify reference acquisition, we aim to estimat…
UW-SDF: Exploiting Hybrid Geometric Priors for Neural SDF Reconstruction from Underwater Multi-view Monocular Images
Zeyu Chen, Jingyi Tang, Gu Wang +4
Due to the unique characteristics of underwater environments, accurate 3D reconstruction of underwater objects poses a challenging problem in tasks such as underwater exploration a…
FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimation
Jingyi Tang, Gu Wang, Zeyu Chen +3
Although methods for estimating the pose of objects in indoor scenes have achieved great success, the pose estimation of underwater objects remains challenging due to difficulties…
LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation
Ruida Zhang, Ziqin Huang, Gu Wang +5
While RGBD-based methods for category-level object pose estimation hold promise, their reliance on depth data limits their applicability in diverse scenarios. In response, recent e…
RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications
Xingyu Liu, Chenyangguang Zhang, Gu Wang +2
In robotic vision, a de-facto paradigm is to learn in simulated environments and then transfer to real-world applications, which poses an essential challenge in bridging the sim-to…
KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation
Ruida Zhang, Chenyangguang Zhang, Yan Di +4
In this paper, we present KP-RED, a unified KeyPoint-driven REtrieval and Deformation framework that takes object scans as input and jointly retrieves and deforms the most geometri…
D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
Bowen Fu, Gu Wang, Chenyangguang Zhang +6
Reconstructing hand-held objects from a single RGB image is a challenging task in computer vision. In contrast to prior works that utilize deterministic modeling paradigms, we empl…
ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation
Yan Di, Chenyangguang Zhang, Chaowei Wang +6
In this paper, we present ShapeMatcher, a unified self-supervised learning framework for joint shape canonicalization, segmentation, retrieval and deformation. Given a partially-ob…
LanPose: Language-Instructed 6D Object Pose Estimation for Robotic Assembly
Bowen Fu, Sek Kun Leong, Yan Di +2
Comprehending natural language instructions is a critical skill for robots to cooperate effectively with humans. In this paper, we aim to learn 6D poses for roboticassembly by natu…
MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision
Chenyangguang Zhang, Guanlong Jiao, Yan Di +7
Previous works concerning single-view hand-held object reconstruction typically rely on supervision from 3D ground-truth models, which are hard to collect in real world. In contras…