Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding

Wen, Xin; Han, Zhizhong; Cao, Yan‐Pei; Wan, Pengfei; Zheng, Wen; Liu, Yu‐Shen

doi:10.1109/cvpr46437.2021.01288

Cited by 89 publications

(34 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a growing attention on the task of point cloud based shape completion [1], [13], [43], [44] in recent years. Since point cloud is a direct output form of many 3D scanning devices, and the storage and process of point clouds require much less computational cost than volumetric data, many recent studies consider to perform direct completion on 3D point clouds.…”

Section: Point Cloud Based Shape Completionmentioning

confidence: 99%

PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths

Xu¹,

Peng²,

Han³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Point cloud completion concerns to predict missing part for incomplete 3D shapes. A common strategy is to generate complete shape according to incomplete input. However, unordered nature of point clouds will degrade generation of high-quality 3D shapes, as detailed topology and structure of unordered points are hard to be captured during the generative process using an extracted latent code. We address this problem by formulating completion as point cloud deformation process. Specifically, we design a novel neural network, named PMP-Net++, to mimic behavior of an earth mover. It moves each point of incomplete input to obtain a complete point cloud, where total distance of point moving paths (PMPs) should be the shortest. Therefore, PMP-Net++ predicts unique PMP for each point according to constraint of point moving distances. The network learns a strict and unique correspondence on point-level, and thus improves quality of predicted complete shape. Moreover, since moving points heavily relies on per-point features learned by network, we further introduce a transformer-enhanced representation learning network, which significantly improves completion performance of PMP-Net++. We conduct comprehensive experiments in shape completion, and further explore application on point cloud up-sampling, which demonstrate non-trivial improvement of PMP-Net++ over state-of-the-art point cloud completion/up-sampling methods.

show abstract

Section: Point Cloud Based Shape Completionmentioning

confidence: 99%

PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths

Xu¹,

Peng²,

Han³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…We exploit the partial matching loss from [7] to preserve the shape structure of the incomplete point cloud, which is defined as…”

Section: Preservation Lossmentioning

confidence: 99%

“…I N 3D computer vision [1], [2], [3], [4] applications, raw point clouds captured by 3D scanners and depth cameras are usually sparse and incomplete [5], [6], [7] due to occlusion and limited sensor resolution. Therefore, point cloud completion [5], [8], which aims to predict a complete shape from its partial observation, is vital for various downstream tasks.…”

Section: Introductionmentioning

confidence: 99%

Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

Peng¹,

Xu²,

Liu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Most existing point cloud completion methods suffered from discrete nature of point clouds and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details. To resolve this issue, we propose SnowflakeNet with Snowflake Point Deconvolution (SPD) to generate the complete point clouds. SPD models the generation of complete point clouds as the snowflake-like growth of points, where the child points are progressively generated by splitting their parent points after each SPD. Our insight of revealing detailed geometry is to introduce skip-transformer in SPD to learn point splitting patterns which can fit local regions the best. Skip-transformer leverages attention mechanism to summarize the splitting patterns used in previous SPD layer to produce the splitting in current SPD layer. The locally compact and structured point clouds generated by SPD precisely reveal the structure characteristic of 3D shape in local patches, which enables us to predict highly detailed geometries. Moreover, since SPD is a general operation, which is not limited to completion, we further explore the applications of SPD on other generative tasks, including point cloud auto-encoding, generation, single image reconstruction and upsampling. Our experimental results outperform the state-of-the-art methods under widely used benchmarks.

show abstract

“…SpareNet [41] proposes a style-based point generator with adversarial rendering for point cloud completion. Cycle4Completion [35] improves the completion quality by establishing the geometric correspondence between complete shapes and incomplete ones.…”

Section: Related Workmentioning

confidence: 99%

Point cloud completion on structured feature map with feedback network

Zejia¹,

Huang²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we tackle the challenging problem of point cloud completion from the perspective of feature learning. Our key observation is that to recover the underlying structures as well as surface details given a partial input, a fundamental component is a good feature representation that can capture both global structure and local geometric details. Towards this end, we first propose FSNet, a feature structuring module that can adaptively aggregate point-wise features into a 2D structured feature map by learning multiple latent patterns from local regions. We then integrate FSNet into a coarse-to-fine pipeline for point cloud completion. Specifically, a 2D convolutional neural network is adopted to decode feature maps from FSNet into a coarse and complete point cloud. Next, a point cloud upsampling network is used to generate dense point cloud from the partial input and the coarse intermediate output. To efficiently exploit the local structures and enhance the point distribution uniformity, we propose IFNet, a point upsampling module with self-correction mechanism that can progressively refine details of the generated dense point cloud.We conduct both qualitative and quantitative experiments on ShapeNet, MVP, and KITTI datasets, which demonstrate that our method outperforms state-of-the-art point cloud completion approaches.

show abstract

Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding

Cited by 89 publications

References 37 publications

PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths

PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths

Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

Point cloud completion on structured feature map with feedback network

Contact Info

Product

Resources

About