# Depth-Adapted CNN for RGB-D cameras

arXiv: https://arxiv.org/abs/2009.09976 · HTML: https://mlsanity.com/paper/2009.09976/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation](https://mlsanity.com/paper/2309.09668/) (2023)
- [Source-free Depth for Object Pop-out](https://mlsanity.com/paper/2212.05370/) (2022)
- [Robust RGB-D Fusion for Saliency Detection](https://mlsanity.com/paper/2208.01762/) (2022)
- [Modality-Guided Subnetwork for Salient Object Detection](https://mlsanity.com/paper/2110.04904/) (2021)
- [Depth-Adapted CNNs for RGB-D Semantic Segmentation](https://mlsanity.com/paper/2206.03939/) (2022)
- [LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing](https://mlsanity.com/paper/2404.13659/) (2024)
- [CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction](https://mlsanity.com/paper/2404.14042/) (2024)
- [Toward Efficient Visual Gyroscopes: Spherical Moments, Harmonics Filtering, and Masking Techniques for Spherical Camera Applications](https://mlsanity.com/paper/2404.01924/) (2024)
- [Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents](https://mlsanity.com/paper/2503.16711/) (2025)
- [SegRGB-X: General RGB-X Semantic Segmentation Model](https://mlsanity.com/paper/2603.28023/) (2026)

## Abstract (arXiv)

Conventional 2D Convolutional Neural Networks (CNN) extract features from an input image by applying linear filters. These filters compute the spatial coherence by weighting the photometric information on a fixed neighborhood without taking into account the geometric information. We tackle the problem of improving the classical RGB CNN methods by using the depth information provided by the RGB-D cameras. State-of-the-art approaches use depth as an additional channel or image (HHA) or pass from 2D CNN to 3D CNN. This paper proposes a novel and generic procedure to articulate both photometric and geometric information in CNN architecture. The depth data is represented as a 2D offset to adapt spatial sampling locations. The new model presented is invariant to scale and rotation around the X and the Y axis of the camera coordinate system. Moreover, when depth data is constant, our model is equivalent to a regular CNN. Experiments of benchmarks validate the effectiveness of our model.