paper-with-me

홈 › Papers

SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer

2022-07-21 · Haoran Zhou, Yun Cao, Wenqing Chu, Junwei Zhu, Tong Lu, Ying Tai, Chengjie Wang

Point cloud completion has become increasingly popular among generation tasks of 3D point clouds, as it is a challenging yet indispensable problem to recover the complete shape of a 3D object from its partial observation. In this paper, we propose a novel SeedFormer to improve the ability of detail preservation and recovery in point cloud completion. Unlike previous methods based on a global feature vector, we introduce a new shape representation, namely Patch Seeds, which not only captures general structures from partial inputs but also preserves regional information of local patterns. Then, by integrating seed features into the generation process, we can recover faithful details for complete point clouds in a coarse-to-fine manner. Moreover, we devise an Upsample Transformer by extending the transformer structure into basic operations of point generators, which effectively incorporates spatial and semantic relationships between neighboring points. Qualitative and quantitative evaluations demonstrate that our method outperforms state-of-the-art completion networks on several benchmark datasets. Our code is available at https://github.com/hrzhou2/seedformer.

📄 PDF Abstract BibTeX arXiv:2207.10315

Code (1)

hrzhou2/seedformer 공식 구현 pytorch

Tasks

Point Cloud Completion

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

High-Fidelity Point Cloud Completion with Low-Resolution Recovery and Noise-Aware Upsampling

2021-12-21 · Ren-Wu Li, Bo wang, Chun-Peng Li, Ling-Xiao Zhang 외

Completing an unordered partial point cloud is a challenging task. Existing approaches that rely on decoding a latent feature to recover the complete shape, often lead to the completed point cloud being over-smoothing, l…

Point Cloud Completion

SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network

2025-02-26 · Ziming Nie, Qiao Wu, Chenlei Lv, Siwen Quan 외

Point cloud upsampling aims to generate dense and uniformly distributed point sets from sparse point clouds. Existing point cloud upsampling methods typically approach the task as an interpolation problem. They achieve u…

point cloud upsampling

P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds

2023-07-27 · ICCV 2023 1 · Ruikai Cui, Shi Qiu, Saeed Anwar, Jiawei Liu 외

Point cloud completion aims to recover the complete shape based on a partial observation. Existing methods require either complete point clouds or multiple partial observations of the same object for learning. In contras…

Point Cloud Completion

Masked Autoencoders in 3D Point Cloud Representation Learning

2022-07-04 · Jincen Jiang, Xuequan Lu, Lizhi Zhao, Richard Dazeley 외

Transformer-based Self-supervised Representation Learning methods learn generic features from unlabeled datasets for providing useful network initialization parameters for downstream tasks. Recently, self-supervised lear…

Point Cloud CompletionPoint cloud reconstructionRepresentation LearningSelf-Supervised Learning

SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification

2020-08-17 · ECCV 2020 8 · Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari

Point clouds are often the default choice for many applications as they exhibit more flexibility and efficiency than volumetric data. Nevertheless, their unorganized nature -- points are stored in an unordered way -- mak…

ClassificationDecoderGeneral ClassificationPoint Cloud Completion