1 code implementation • 18 Dec 2023 • Guo Pu, Peng-Shuai Wang, Zhouhui Lian
This paper proposes SinMPI, a novel method that uses an expanded multiplane image (MPI) as the 3D scene representation to significantly expand the perspective range of MPI and generate high-quality novel views from a large multiplane space.
3 code implementations • 15 Dec 2023 • Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao
This paper is not motivated to seek innovation within the attention mechanism.
Ranked #1 on Semantic Segmentation on S3DIS (using extra training data)
1 code implementation • 11 Sep 2023 • Bo Pang, Zhongtian Zheng, Guoping Wang, Peng-Shuai Wang
Then, we can compute the geodesic distance between a pair of points using our decoding function, which requires only several matrix multiplications and can be massively parallelized on GPUs.
no code implementations • 8 May 2023 • Xin-Yang Zheng, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu, Heung-Yeung Shum
Our method is built on a two-stage diffusion model.
3 code implementations • 4 May 2023 • Peng-Shuai Wang
To combat this issue, several works divide point clouds into non-overlapping windows and constrain attentions in each local window.
Ranked #5 on 3D Semantic Segmentation on ScanNet200
no code implementations • 14 Apr 2023 • Siming Yan, YuQi Yang, YuXiao Guo, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu, QiXing Huang
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.
2 code implementations • 14 Apr 2023 • Yu-Qi Yang, Yu-Xiao Guo, Jian-Yu Xiong, Yang Liu, Hao Pan, Peng-Shuai Wang, Xin Tong, Baining Guo
We pretrained a large {\SST} model on a synthetic Structured3D dataset, which is an order of magnitude larger than the ScanNet dataset.
Ranked #2 on 3D Object Detection on S3DIS (using extra training data)
1 code implementation • ICCV 2023 • Huimin Wu, Chenyang Lei, Xiao Sun, Peng-Shuai Wang, Qifeng Chen, Kwang-Ting Cheng, Stephen Lin, Zhirong Wu
Self-supervised representation learning follows a paradigm of withholding some part of the data and tasking the network to predict it from the remaining part.
1 code implementation • 24 Jun 2022 • Xin-Yang Zheng, Yang Liu, Peng-Shuai Wang, Xin Tong
We further complement the evaluation metrics of 3D generative models with the shading-image-based Fr\'echet inception distance (FID) scores to better assess visual quality and shape distribution of the generated shapes.
1 code implementation • 5 May 2022 • Peng-Shuai Wang, Yang Liu, Xin Tong
Our method encodes the volumetric field of a 3D shape with an adaptive feature volume organized by an octree and applies a compact multilayer perceptron network for mapping the features to the field value at each 3D position.
1 code implementation • 19 Apr 2022 • Chun-Yu Sun, Yu-Qi Yang, Hao-Xiang Guo, Peng-Shuai Wang, Xin Tong, Yang Liu, Heung-Yeung Shum
We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data.
1 code implementation • ICCV 2021 • Yu-Qi Yang, Peng-Shuai Wang, Yang Liu
For fine-grained 3D vision tasks where point-wise features are essential, like semantic segmentation and 3D detection, our network achieves higher prediction accuracy than the existing networks using the nearest neighbor interpolation or the normalized trilinear interpolation with the zero-padding or the octree-padding scheme.
1 code implementation • 3 Jun 2021 • Peng-Shuai Wang, Yang Liu, Yu-Qi Yang, Xin Tong
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 occupancy values.
1 code implementation • CVPR 2021 • Shi-Lin Liu, Hao-Xiang Guo, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu
We incorporate IMLS surface generation into deep neural networks for inheriting both the flexibility of point sets and the high quality of implicit surfaces.
1 code implementation • 3 Aug 2020 • Peng-Shuai Wang, Yu-Qi Yang, Qian-Fang Zou, Zhirong Wu, Yang Liu, Xin Tong
Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various shape analysis tasks with competitive performance to supervised methods.
Ranked #2 on 3D Semantic Segmentation on PartNet
3D Point Cloud Linear Classification 3D Semantic Segmentation
1 code implementation • 6 Jun 2020 • 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.
1 code implementation • 21 Sep 2018 • Peng-Shuai Wang, Chun-Yu Sun, Yang Liu, Xin Tong
The Adaptive O-CNN encoder takes the planar patch normal and displacement as input and performs 3D convolutions only at the octants at each level, while the Adaptive O-CNN decoder infers the shape occupancy and subdivision status of octants at each level and estimates the best plane normal and displacement for each leaf octant.
1 code implementation • 5 Dec 2017 • Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis.
Ranked #4 on 3D Object Classification on ModelNet40
no code implementations • 15 Nov 2016 • Peng-Shuai Wang, Yang Liu, Xin Tong
At runtime, our method applies the learned cascaded regression functions to a noisy input mesh and reconstructs the denoised mesh from the output facet normals.