# PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors

arXiv: https://arxiv.org/abs/2411.19036 · HTML: https://mlsanity.com/paper/2411.19036/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 49 of its 58 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 49)

- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://mlsanity.com/paper/2303.13439/) (2023)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [ControlVideo: Training-free Controllable Text-to-Video Generation](https://mlsanity.com/paper/2305.13077/) (2023)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion](https://mlsanity.com/paper/2311.07885/) (2023)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model](https://mlsanity.com/paper/2403.05034/) (2024)
- [MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion](https://mlsanity.com/paper/2307.01097/) (2023)
- [GRNet: Gridding Residual Network for Dense Point Cloud Completion](https://mlsanity.com/paper/2006.03761/) (2020)
- [RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D](https://mlsanity.com/paper/2311.16918/) (2023)
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)

## Built on by (most cited first, 16 of 16)

- [PointSea: Point Cloud Completion via Self-structure Augmentation](https://mlsanity.com/paper/2502.17053/) (2025)
- [LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency](https://mlsanity.com/paper/2602.18735/) (2026)
- [DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion](https://mlsanity.com/paper/2509.23723/) (2025)
- [Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective](https://mlsanity.com/paper/2511.12170/) (2025)
- [Flexible-weighted Chamfer Distance: Enhanced Objective Function for Point Cloud Completion](https://mlsanity.com/paper/2505.14218/) (2025)
- [Artist-Created Mesh Generation from Raw Observation](https://mlsanity.com/paper/2509.12501/) (2025)
- [Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion](https://mlsanity.com/paper/2511.16161/) (2025)
- [HeartFormer: Semantic-Aware Dual-Structure Transformers for 3D Four-Chamber Cardiac Point Cloud Reconstruction](https://mlsanity.com/paper/2512.00264/) (2025)
- [Repurposing 2D Diffusion Models for 3D Shape Completion](https://mlsanity.com/paper/2512.13991/) (2025)
- [DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion](https://mlsanity.com/paper/2511.07978/) (2025)
- [Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completion](https://mlsanity.com/paper/2511.14152/) (2025)
- [PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration](https://mlsanity.com/paper/2605.25127/) (2026)
- [ProjFormer: Point Cloud Completion via Geometric-Projective Transformer and Cross-Modal Semantic Constraints](https://mlsanity.com/paper/2608.15104/) (2026)
- [DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perception](https://mlsanity.com/paper/2608.31002/) (2026)
- [UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound](https://mlsanity.com/paper/2609.11506/) (2026)
- [ScaleBlind: Point Cloud Completion under Unknown Scale](https://mlsanity.com/paper/2609.23404/) (2026)

## Abstract (arXiv)

This paper presents PCDreamer, a novel method for point cloud completion. Traditional methods typically extract features from partial point clouds to predict missing regions, but the large solution space often leads to unsatisfactory results. More recent approaches have started to use images as extra guidance, effectively improving performance, but obtaining paired data of images and partial point clouds is challenging in practice. To overcome these limitations, we harness the relatively view-consistent multi-view diffusion priors within large models, to generate novel views of the desired shape. The resulting image set encodes both global and local shape cues, which are especially beneficial for shape completion. To fully exploit the priors, we have designed a shape fusion module for producing an initial complete shape from multi-modality input (i.e.,, images and point clouds), and a follow-up shape consolidation module to obtain the final complete shape by discarding unreliable points introduced by the inconsistency from diffusion priors. Extensive experimental results demonstrate our superior performance, especially in recovering fine details.