# I2PRef: Image-Driven Point Completion with Iterative Refinement

arXiv: https://arxiv.org/abs/2605.26914 · HTML: https://mlsanity.com/paper/2605.26914/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [3D Shape Generation and Completion through Point-Voxel Diffusion](https://mlsanity.com/paper/2104.03670/) (2021)
- [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)
- [AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation](https://mlsanity.com/paper/2203.09516/) (2022)
- [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)
- [Morphing and Sampling Network for Dense Point Cloud Completion](https://mlsanity.com/paper/1912.00280/) (2019)
- [Cascaded Refinement Network for Point Cloud Completion](https://mlsanity.com/paper/2004.03327/) (2020)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion](https://mlsanity.com/paper/2112.03530/) (2021)
- [Unsupervised 3D Shape Completion through GAN Inversion](https://mlsanity.com/paper/2104.13366/) (2021)
- [AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers](https://mlsanity.com/paper/2301.04545/) (2023)
- [PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths](https://mlsanity.com/paper/2202.09507/) (2022)
- [PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection](https://mlsanity.com/paper/2303.08129/) (2023)
- [View-Guided Point Cloud Completion](https://mlsanity.com/paper/2104.05666/) (2021)
- [ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer](https://mlsanity.com/paper/2302.14435/) (2023)
- [Cross-modal Learning for Image-Guided Point Cloud Shape Completion](https://mlsanity.com/paper/2209.09552/) (2022)
- [DiffComplete: Diffusion-based Generative 3D Shape Completion](https://mlsanity.com/paper/2306.16329/) (2023)
- [SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator](https://mlsanity.com/paper/2307.08492/) (2023)
- [CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completion](https://mlsanity.com/paper/2208.00751/) (2022)
- [Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion](https://mlsanity.com/paper/2407.02887/) (2024)
- [RGB2Point: 3D Point Cloud Generation from Single RGB Images](https://mlsanity.com/paper/2407.14979/) (2024)
- [Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability](https://mlsanity.com/paper/2601.20642/) (2026)

## Built on by (most cited first, 1 of 1)

- [Towards Real-Time and Adaptable LiDAR Scene Completion](https://mlsanity.com/paper/2608.16490/) (2026)

## Abstract (arXiv)

We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete point clouds directly from a single RGB image, with no need for 3D inputs. Additionally, we introduce a transformer-based Point-to-Point (P2P) refinement module that uses self- and cross-attention between point tokens and image features to iteratively refine the coarse I2P output. The I2P module enables the image encoder to learn rich geometric representations, while the P2P module progressively recovers fine-grained details. Unlike existing multimodal methods that rely on auxiliary losses or fusion modules, our explicit I2P task provides a strong, geometry-aware prior based on images alone. Extensive experiments on ShapeNet-ViPC demonstrate state-of-the-art completion performance with a 12.3% relative Chamfer Distance improvement over prior methods. Code is available at: https://github.com/AzharSindhi/I2PRef.git