# RL-AD-Net: Reinforcement Learning Guided Adaptive Displacement in Latent Space for Refined Point Cloud Completion

arXiv: https://arxiv.org/abs/2511.17054 · HTML: https://mlsanity.com/paper/2511.17054/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 14 of 14)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [CLIP-Mesh: Generating textured meshes from text using pretrained image-text models](https://mlsanity.com/paper/2203.13333/) (2022)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer](https://mlsanity.com/paper/2207.10315/) (2022)
- [RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion](https://mlsanity.com/paper/1904.12304/) (2019)
- [Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis](https://mlsanity.com/paper/2303.08134/) (2023)
- [SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification](https://mlsanity.com/paper/2008.07358/) (2020)
- [Voxel-based Network for Shape Completion by Leveraging Edge Generation](https://mlsanity.com/paper/2108.09936/) (2021)
- [RGB2Point: 3D Point Cloud Generation from Single RGB Images](https://mlsanity.com/paper/2407.14979/) (2024)
- [PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds](https://mlsanity.com/paper/2410.18800/) (2024)

## Abstract (arXiv)

Recent point cloud completion models, including transformer-based, denoising-based, and other state-of-the-art approaches, generate globally plausible shapes from partial inputs but often leave local geometric inconsistencies. We propose RL-AD-Net, a reinforcement learning (RL) refinement framework that operates in the latent space of a pretrained point autoencoder. The autoencoder encodes completions into compact global feature vectors (GFVs), which are selectively adjusted by an RL agent to improve geometric fidelity. To ensure robustness, a lightweight non-parametric PointNN selector evaluates the geometric consistency of both the original completion and the RL-refined output, retaining the better reconstruction. When ground truth is available, both Chamfer Distance and geometric consistency metrics guide refinement. Training is performed separately per category, since the unsupervised and dynamic nature of RL makes convergence across highly diverse categories challenging. Nevertheless, the framework can be extended to multi-category refinement in future work. Experiments on ShapeNetCore-2048 demonstrate that while baseline completion networks perform reasonable under their training-style cropping, they struggle in random cropping scenarios. In contrast, RL-AD-Net consistently delivers improvements across both settings, highlighting the effectiveness of RL-guided ensemble refinement. The approach is lightweight, modular, and model-agnostic, making it applicable to a wide range of completion networks without requiring retraining.