120 citations · 387 across the 21 of their papers we have counts for
21 papers
Neural Centroidal Voronoi Tessellations
Jiacheng Xu, Bo Pang, Rui Xu +5
Centroidal Voronoi tessellation (CVT) is a fundamental primitive for high-quality surface sampling and isotropic remeshing in computer graphics. However, computing surface CVTs wit…
MVD: Efficient Multiview 3D Reconstruction for Multiview Diffusion
Xin-Yang Zheng, Hao Pan, Yu-Xiao Guo +2
As a promising 3D generation technique, multiview diffusion (MVD) has received a lot of attention due to its advantages in terms of generalizability, quality, and efficiency. By fi…
Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding
Yu-Qi Yang, Yu-Xiao Guo, Yang Liu
Data diversity and abundance are essential for improving the performance and generalization of models in natural language processing and 2D vision. However, 3D vision domain suffer…
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation
Mutian Xu, Xingyilang Yin, Lingteng Qiu +3
We introduce SAMPro3D for zero-shot instance segmentation of 3D scenes. Given the 3D point cloud and multiple posed RGB-D frames of 3D scenes, our approach segments 3D instances by…
StructRe: Rewriting for Structured Shape Modeling
Jiepeng Wang, Hao Pan, Yang Liu +3
Man-made 3D shapes are naturally organized in parts and hierarchies; such structures provide important constraints for shape reconstruction and generation. Modeling shape structure…
Locally Attentional SDF Diffusion for Controllable 3D Shape Generation
Xin-Yang Zheng, Hao Pan, Peng-Shuai Wang +3
Although the recent rapid evolution of 3D generative neural networks greatly improves 3D shape generation, it is still not convenient for ordinary users to create 3D shapes and con…
3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
Siming Yan, Yuqi Yang, Yuxiao Guo +5
Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used i…
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding
Yu-Qi Yang, Yu-Xiao Guo, Jian-Yu Xiong +5
The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this wo…
Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation
Chunyu Sun, Xin Tong, Yang Liu
Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance ce…
SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation
Xin-Yang Zheng, Yang Liu, Peng-Shuai Wang +1
We present a StyleGAN2-based deep learning approach for 3D shape generation, called SDF-StyleGAN, with the aim of reducing visual and geometric dissimilarity between generated shap…
ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation
Haoxiang Guo, Shilin Liu, Hao Pan +3
We view the reconstruction of CAD models in the boundary representation (B-Rep) as the detection of geometric primitives of different orders, i.e. vertices, edges and surface patch…
Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations
Peng-Shuai Wang, Yang Liu, Xin Tong
We present an adaptive deep representation of volumetric fields of 3D shapes and an efficient approach to learn this deep representation for high-quality 3D shape reconstruction an…
Semi-supervised 3D shape segmentation with multilevel consistency and part substitution
Chun-Yu Sun, Yu-Qi Yang, Hao-Xiang Guo +4
The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for…
Sketch2PQ: Freeform Planar Quadrilateral Mesh Design via a Single Sketch
Zhi Deng, Yang Liu, Hao Pan +3
The freeform architectural modeling process often involves two important stages: concept design and digital modeling. In the first stage, architects usually sketch the overall 3D s…
Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks
Yu-Qi Yang, Peng-Shuai Wang, Yang Liu
Sparse voxel-based 3D convolutional neural networks (CNNs) are widely used for various 3D vision tasks. Sparse voxel-based 3D CNNs create sparse non-empty voxels from the 3D input…
Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields
Peng-Shuai Wang, Yang Liu, Yu-Qi Yang +1
Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or…
Deep Implicit Moving Least-Squares Functions for 3D Reconstruction
Shi-Lin Liu, Hao-Xiang Guo, Hao Pan +3
Point set is a flexible and lightweight representation widely used for 3D deep learning. However, their discrete nature prevents them from representing continuous and fine geometry…
Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination
Peng-Shuai Wang, Yu-Qi Yang, Qian-Fang Zou +3
Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learnin…
Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion
Peng-Shuai Wang, Yang Liu, Xin Tong
Acquiring complete and clean 3D shape and scene data is challenging due to geometric occlusion and insufficient views during 3D capturing. We present a simple yet effective deep le…
OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples
Changjian Chen, Jun Yuan, Yafeng Lu +4
One major cause of performance degradation in predictive models is that the test samples are not well covered by the training data. Such not well-represented samples are called OoD…
Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
Peng-Shuai Wang, Chun-Yu Sun, Yang Liu +1
We present an Adaptive Octree-based Convolutional Neural Network (Adaptive O-CNN) for efficient 3D shape encoding and decoding. Different from volumetric-based or octree-based CNN…