# Privacy-Preserving Semantic Segmentation from High-Resolution Depth and Ultra-Low-Resolution RGB

arXiv: https://arxiv.org/abs/2609.28360 · HTML: https://mlsanity.com/paper/2609.28360/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 23 Sep 2026.

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

- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation](https://mlsanity.com/paper/1803.10409/) (2018)
- [DeepPrivacy: A Generative Adversarial Network for Face Anonymization](https://mlsanity.com/paper/1909.04538/) (2019)
- [Fast Point Transformer](https://mlsanity.com/paper/2112.04702/) (2021)
- [Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis](https://mlsanity.com/paper/2011.06961/) (2020)
- [Recurrent Slice Networks for 3D Segmentation of Point Clouds](https://mlsanity.com/paper/1802.04402/) (2018)
- [Multi-view PointNet for 3D Scene Understanding](https://mlsanity.com/paper/1909.13603/) (2019)
- [DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation](https://mlsanity.com/paper/2309.09668/) (2023)
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://mlsanity.com/paper/2204.07548/) (2022)
- [TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes](https://mlsanity.com/paper/1812.00020/) (2018)
- [DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation](https://mlsanity.com/paper/2504.04701/) (2025)
- [Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images](https://mlsanity.com/paper/1712.01066/) (2017)
- [Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning](https://mlsanity.com/paper/1708.00999/) (2017)
- [PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks](https://mlsanity.com/paper/2606.13108/) (2026)
- [Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?](https://mlsanity.com/paper/2309.13038/) (2023)
- [TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2407.09751/) (2024)
- [MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments](https://mlsanity.com/paper/2503.13816/) (2025)
- [Designing Privacy-Preserving Visual Perception for Robot Navigation Based on User Privacy Preferences](https://mlsanity.com/paper/2604.06382/) (2026)
- [The Need for Inherently Privacy-Preserving Vision in Trustworthy Autonomous Systems](https://mlsanity.com/paper/2303.16408/) (2023)
- [Privacy-Preserving Semantic Segmentation from Ultra-Low-Resolution RGB Inputs](https://mlsanity.com/paper/2507.16034/) (2025)
- [Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applications](https://mlsanity.com/paper/2607.00978/) (2026)

## Abstract (arXiv)

As mobile robots become increasingly integrated into everyday environments, privacy risks arising from onboard cameras have become a growing concern. Ultra-low-resolution (ULR) RGB can mitigate visual privacy exposure at the source, but ULR appearance alone substantially limits semantic and spatial understanding. We therefore introduce a privacy-preserving asymmetric sensing setting that combines high-resolution (HR) depth with ULR RGB, preserving dense geometry while restricting fine-grained visual information. To address the severe information imbalance between HR depth and ULR RGB, we propose a joint 2D framework using HR geometry to guide semantic-oriented RGB reconstruction and RGB-D segmentation. Despite reliable frame-level predictions, consistent scene-level understanding remains challenging under the asymmetric HR depth--ULR RGB setting. We therefore develop an end-to-end 2D-to-3D pipeline that consolidates 2D semantic features for 3D segmentation. Experiments on ScanNet show that our method achieves the best 2D and 3D segmentation performance among privacy-preserving approaches and delivers the strongest zero-shot transfer to SUN RGB-D and SceneNN. Privacy recoverability analysis shows that our proposed HR depth--ULR RGB input reduces the recoverability of sensitive data, and real-robot experiments demonstrate the utility of the resulting 3D semantics for object-goal navigation.