Point Cloud Upsampling via Cascaded Refinement Network

by   Hang Du, et al.

Point cloud upsampling focuses on generating a dense, uniform and proximity-to-surface point set. Most previous approaches accomplish these objectives by carefully designing a single-stage network, which makes it still challenging to generate a high-fidelity point distribution. Instead, upsampling point cloud in a coarse-to-fine manner is a decent solution. However, existing coarse-to-fine upsampling methods require extra training strategies, which are complicated and time-consuming during the training. In this paper, we propose a simple yet effective cascaded refinement network, consisting of three generation stages that have the same network architecture but achieve different objectives. Specifically, the first two upsampling stages generate the dense but coarse points progressively, while the last refinement stage further adjust the coarse points to a better position. To mitigate the learning conflicts between multiple stages and decrease the difficulty of regressing new points, we encourage each stage to predict the point offsets with respect to the input shape. In this manner, the proposed cascaded refinement network can be easily optimized without extra learning strategies. Moreover, we design a transformer-based feature extraction module to learn the informative global and local shape context. In inference phase, we can dynamically adjust the model efficiency and effectiveness, depending on the available computational resources. Extensive experiments on both synthetic and real-scanned datasets demonstrate that the proposed approach outperforms the existing state-of-the-art methods.


Point Cloud Upsampling via Disentangled Refinement

Point clouds produced by 3D scanning are often sparse, non-uniform, and ...

Morphing and Sampling Network for Dense Point Cloud Completion

3D point cloud completion, the task of inferring the complete geometric ...

Cascaded Refinement Network for Point Cloud Completion

Point clouds are often sparse and incomplete. Existing shape completion ...

CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm

Point cloud completion aims to predict complete shape from its partial o...

SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization

The task of point cloud upsampling aims to acquire dense and uniform poi...

Adversarial Refinement Network for Human Motion Prediction

Human motion prediction aims to predict future 3D skeletal sequences by ...

Cloud Sphere: A 3D Shape Representation via Progressive Deformation

In the area of 3D shape analysis, the geometric properties of a shape ha...

Please sign up or login with your details

Forgot password? Click here to reset