107 citations · 346 across the 23 of their papers we have counts for
24 papers
LARM: A Large Articulated-Object Reconstruction Model
Sylvia Yuan, Ruoxi Shi, Xinyue Wei +3
Modeling 3D articulated objects with realistic geometry, textures, and kinematics is essential for a wide range of applications. However, existing optimization-based reconstruction…
FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion
Chuhao Chen, Isabella Liu, Xinyue Wei +2
Articulated 3D objects are central to many applications in robotics, AR/VR, and animation. Recent approaches to modeling such objects either rely on optimization-based reconstructi…
PartUV: Part-Based UV Unwrapping of 3D Meshes
Zhaoning Wang, Xinyue Wei, Ruoxi Shi +3
UV unwrapping flattens 3D surfaces to 2D with minimal distortion, often requiring the complex surface to be decomposed into multiple charts. Although extensively studied, existing…
PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU
Seonghun Oh, Xiaodi Yuan, Xinyue Wei +4
Reducing the triangle count in complex 3D models is a basic geometry preprocessing step in graphics pipelines such as efficient rendering and interactive editing. However, most exi…
PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond
Minghua Liu, Mikaela Angelina Uy, Donglai Xiang +4
We propose PartField, a feedforward approach for learning part-based 3D features, which captures the general concept of parts and their hierarchy without relying on predefined temp…
MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Minghua Liu, Chong Zeng, Xinyue Wei +9
Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive trainin…
SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views
Chao Xu, Ang Li, Linghao Chen +4
Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient c…
DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
Tongzhou Mu, Minghua Liu, Hao Su
The success of many RL techniques heavily relies on human-engineered dense rewards, which typically demand substantial domain expertise and extensive trial and error. In our work,…
PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation
Yuchen Zhou, Jiayuan Gu, Xuanlin Li +3
Open-world 3D part segmentation is pivotal in diverse applications such as robotics and AR/VR. Traditional supervised methods often grapple with limited 3D data availability and st…
One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion
Minghua Liu, Ruoxi Shi, Linghao Chen +7
Recent advancements in open-world 3D object generation have been remarkable, with image-to-3D methods offering superior fine-grained control over their text-to-3D counterparts. How…
Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
Ruoxi Shi, Hansheng Chen, Zhuoyang Zhang +6
We report Zero123++, an image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view. To take full advantage of pretrained 2D generativ…
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability
Xuanlin Li, Yunhao Fang, Minghua Liu +3
Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sen…
One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
Minghua Liu, Chao Xu, Haian Jin +4
Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a…
OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
Minghua Liu, Ruoxi Shi, Kaiming Kuang +6
We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framew…
PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models
Minghua Liu, Yinhao Zhu, Hong Cai +4
Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets wi…
LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds
Minghua Liu, Yin Zhou, Charles R. Qi +3
Semantic segmentation of LiDAR point clouds is an important task in autonomous driving. However, training deep models via conventional supervised methods requires large datasets wh…
Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds
Minghua Liu, Xuanlin Li, Zhan Ling +2
We study how choices of input point cloud coordinate frames impact learning of manipulation skills from 3D point clouds. There exist a variety of coordinate frame choices to normal…
Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search
Xinyue Wei, Minghua Liu, Zhan Ling +1
Approximate convex decomposition aims to decompose a 3D shape into a set of almost convex components, whose convex hulls can then be used to represent the input shape. It thus enab…
Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation
Xiaoshuai Zhang, Rui Chen, Ang Li +11
In this paper, we focus on the simulation of active stereovision depth sensors, which are popular in both academic and industry communities. Inspired by the underlying mechanism of…
DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates
Minghua Liu, Minhyuk Sung, Radomir Mech +1
We propose DeepMetaHandles, a 3D conditional generative model based on mesh deformation. Given a collection of 3D meshes of a category and their deformation handles (control points…
Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance
Minghua Liu, Xiaoshuai Zhang, Hao Su
We are interested in reconstructing the mesh representation of object surfaces from point clouds. Surface reconstruction is a prerequisite for downstream applications such as rende…
SAPIEN: A SimulAted Part-based Interactive ENvironment
Fanbo Xiang, Yuzhe Qin, Kaichun Mo +11
Building home assistant robots has long been a pursuit for vision and robotics researchers. To achieve this task, a simulated environment with physically realistic simulation, suff…
Morphing and Sampling Network for Dense Point Cloud Completion
Minghua Liu, Lu Sheng, Sheng Yang +2
3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community. For acquiring high-fidelit…
Multi-task Batch Reinforcement Learning with Metric Learning
Jiachen Li, Quan Vuong, Shuang Liu +5
We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks…