# Learning Continuous Depth Representation via Geometric Spatial Aggregator

arXiv: https://arxiv.org/abs/2212.03499 · HTML: https://mlsanity.com/paper/2212.03499/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Meta-SR: A Magnification-Arbitrary Network for Super-Resolution](https://mlsanity.com/paper/1903.00875/) (2019)
- [CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction](https://mlsanity.com/paper/1704.03489/) (2017)
- [Learning Rich Features from RGB-D Images for Object Detection and Segmentation](https://mlsanity.com/paper/1407.5736/) (2014)
- [Pixel-Adaptive Convolutional Neural Networks](https://mlsanity.com/paper/1904.05373/) (2019)
- [3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior](https://mlsanity.com/paper/2003.14052/) (2020)
- [Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion](https://mlsanity.com/paper/1910.04066/) (2019)
- [Discrete Cosine Transform Network for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2104.06977/) (2021)
- [Learning A Single Network for Scale-Arbitrary Super-Resolution](https://mlsanity.com/paper/2004.03791/) (2020)
- [Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline](https://mlsanity.com/paper/2104.06174/) (2021)
- [Deformable Kernel Networks for Joint Image Filtering](https://mlsanity.com/paper/1910.08373/) (2019)
- [Joint Image Filtering with Deep Convolutional Networks](https://mlsanity.com/paper/1710.04200/) (2017)
- [RoutedFusion: Learning Real-time Depth Map Fusion](https://mlsanity.com/paper/2001.04388/) (2020)
- [VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction](https://mlsanity.com/paper/2108.08623/) (2021)
- [Joint Implicit Image Function for Guided Depth Super-Resolution](https://mlsanity.com/paper/2107.08717/) (2021)
- [High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusion](https://mlsanity.com/paper/2104.01530/) (2021)
- [X-volution: On the unification of convolution and self-attention](https://mlsanity.com/paper/2106.02253/) (2021)

## Built on by (most cited first, 7 of 7)

- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [DuCos: Duality Constrained Depth Super-Resolution via Foundation Model](https://mlsanity.com/paper/2503.04171/) (2025)
- [RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methods](https://mlsanity.com/paper/2405.10357/) (2024)
- [SpatioTemporal Difference Network for Video Depth Super-Resolution](https://mlsanity.com/paper/2508.01259/) (2025)
- [Multi-Order Matching Network for Alignment-Free Depth Super-Resolution](https://mlsanity.com/paper/2511.16361/) (2025)
- [Towards Generalized Multimodal Homography Estimation](https://mlsanity.com/paper/2603.03956/) (2026)
- [FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolution](https://mlsanity.com/paper/2609.32323/) (2026)

## Abstract (arXiv)

Depth map super-resolution (DSR) has been a fundamental task for 3D computer vision. While arbitrary scale DSR is a more realistic setting in this scenario, previous approaches predominantly suffer from the issue of inefficient real-numbered scale upsampling. To explicitly address this issue, we propose a novel continuous depth representation for DSR. The heart of this representation is our proposed Geometric Spatial Aggregator (GSA), which exploits a distance field modulated by arbitrarily upsampled target gridding, through which the geometric information is explicitly introduced into feature aggregation and target generation. Furthermore, bricking with GSA, we present a transformer-style backbone named GeoDSR, which possesses a principled way to construct the functional mapping between local coordinates and the high-resolution output results, empowering our model with the advantage of arbitrary shape transformation ready to help diverse zooming demand. Extensive experimental results on standard depth map benchmarks, e.g., NYU v2, have demonstrated that the proposed framework achieves significant restoration gain in arbitrary scale depth map super-resolution compared with the prior art. Our codes are available at https://github.com/nana01219/GeoDSR.