# Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective

arXiv: https://arxiv.org/abs/2511.12170 · HTML: https://mlsanity.com/paper/2511.12170/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [PF-Net: Point Fractal Network for 3D Point Cloud Completion](https://mlsanity.com/paper/2003.00410/) (2020)
- [SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer](https://mlsanity.com/paper/2207.10315/) (2022)
- [Shape Completion Enabled Robotic Grasping](https://mlsanity.com/paper/1609.08546/) (2016)
- [3D Point Cloud Processing and Learning for Autonomous Driving](https://mlsanity.com/paper/2003.00601/) (2020)
- [View-Guided Point Cloud Completion](https://mlsanity.com/paper/2104.05666/) (2021)
- [RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction](https://mlsanity.com/paper/2011.14744/) (2020)
- [CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers](https://mlsanity.com/paper/2401.01552/) (2024)
- [PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors](https://mlsanity.com/paper/2411.19036/) (2024)
- [SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance](https://mlsanity.com/paper/2503.18007/) (2025)
- [Learning quadrangulated patches for 3D shape parameterization and completion](https://mlsanity.com/paper/1709.06868/) (2017)
- [DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer](https://mlsanity.com/paper/2406.17319/) (2024)

## Built on by (most cited first, 4 of 4)

- [VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection](https://mlsanity.com/paper/2605.09461/) (2026)
- [DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization](https://mlsanity.com/paper/2605.11015/) (2026)
- [MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement](https://mlsanity.com/paper/2607.02568/) (2026)
- [UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound](https://mlsanity.com/paper/2609.11506/) (2026)

## Abstract (arXiv)

Point cloud completion aims to reconstruct complete 3D shapes from partial observations, which is a challenging problem due to severe occlusions and missing geometry. Despite recent advances in multimodal techniques that leverage complementary RGB images to compensate for missing geometry, most methods still follow a Completion-by-Inpainting paradigm, synthesizing missing structures from fused latent features. We empirically show that this paradigm often results in structural inconsistencies and topological artifacts due to limited geometric and semantic constraints. To address this, we rethink the task and propose a more robust paradigm, termed Completion-by-Correction, which begins with a topologically complete shape prior generated by a pretrained image-to-3D model and performs feature-space correction to align it with the partial observation. This paradigm shifts completion from unconstrained synthesis to guided refinement, enabling structurally consistent and observation-aligned reconstruction. Building upon this paradigm, we introduce PGNet, a multi-stage framework that conducts dual-feature encoding to ground the generative prior, synthesizes a coarse yet structurally aligned scaffold, and progressively refines geometric details via hierarchical correction. Experiments on the ShapeNetViPC dataset demonstrate the superiority of PGNet over state-of-the-art baselines in terms of average Chamfer Distance (-23.5%) and F-score (+7.1%).