# iDisc: Internal Discretization for Monocular Depth Estimation

arXiv: https://arxiv.org/abs/2304.06334 · HTML: https://mlsanity.com/paper/2304.06334/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 70 references that are in the map.
- First posted on arXiv 13 Apr 2023.

## Builds on (most cited first, 30 of 53)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [DIODE: A Dense Indoor and Outdoor DEpth Dataset](https://mlsanity.com/paper/1908.00463/) (2019)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing](https://mlsanity.com/paper/1805.04409/) (2018)
- [Fast Convergence of DETR with Spatially Modulated Co-Attention](https://mlsanity.com/paper/2101.07448/) (2021)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Rethinking Transformer-based Set Prediction for Object Detection](https://mlsanity.com/paper/2011.10881/) (2020)
- [NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation](https://mlsanity.com/paper/2203.01502/) (2022)

## Built on by (most cited first, 30 of 73)

- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler](https://mlsanity.com/paper/2502.20110/) (2025)
- [HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting](https://mlsanity.com/paper/2403.12722/) (2024)
- [UniK3D: Universal Camera Monocular 3D Estimation](https://mlsanity.com/paper/2503.16591/) (2025)
- [PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation](https://mlsanity.com/paper/2312.02284/) (2023)
- [Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera](https://mlsanity.com/paper/2501.02464/) (2025)
- [A General Protocol to Probe Large Vision Models for 3D Physical Understanding](https://mlsanity.com/paper/2310.06836/) (2023)
- [Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion](https://mlsanity.com/paper/2312.12471/) (2023)
- [DepthMaster: Taming Diffusion Models for Monocular Depth Estimation](https://mlsanity.com/paper/2501.02576/) (2025)
- [PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation](https://mlsanity.com/paper/2406.06679/) (2024)
- [Vision-Language Embodiment for Monocular Depth Estimation](https://mlsanity.com/paper/2503.16535/) (2025)
- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation](https://mlsanity.com/paper/2407.08187/) (2024)
- [Learnable Differencing Center for Nighttime Depth Perception](https://mlsanity.com/paper/2306.14538/) (2023)
- [PolyMaX: General Dense Prediction with Mask Transformer](https://mlsanity.com/paper/2311.05770/) (2023)
- [EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment](https://mlsanity.com/paper/2312.08548/) (2023)
- [VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2401.02702/) (2024)
- [BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation](https://mlsanity.com/paper/2405.09546/) (2024)
- [FutureDepth: Learning to Predict the Future Improves Video Depth Estimation](https://mlsanity.com/paper/2403.12953/) (2024)
- [DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain](https://mlsanity.com/paper/2410.14980/) (2024)
- [Diffusion-Based Depth Inpainting for Transparent and Reflective Objects](https://mlsanity.com/paper/2410.08567/) (2024)
- [Scalable Autoregressive Monocular Depth Estimation](https://mlsanity.com/paper/2411.11361/) (2024)
- [RSRD: A Road Surface Reconstruction Dataset and Benchmark for Safe and Comfortable Autonomous Driving](https://mlsanity.com/paper/2310.02262/) (2023)
- [Joint Depth Prediction and Semantic Segmentation with Multi-View SAM](https://mlsanity.com/paper/2311.00134/) (2023)
- [RoadBEV: Road Surface Reconstruction in Bird's Eye View](https://mlsanity.com/paper/2404.06605/) (2024)
- [SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2404.12501/) (2024)
- [Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration](https://mlsanity.com/paper/2411.17240/) (2024)
- [UniDAC: Universal Metric Depth Estimation for Any Camera](https://mlsanity.com/paper/2603.27105/) (2026)
- [PCDepth: Pattern-based Complementary Learning for Monocular Depth Estimation by Best of Both Worlds](https://mlsanity.com/paper/2402.18925/) (2024)

## Abstract (arXiv)

Monocular depth estimation is fundamental for 3D scene understanding and downstream applications. However, even under the supervised setup, it is still challenging and ill-posed due to the lack of full geometric constraints. Although a scene can consist of millions of pixels, there are fewer high-level patterns. We propose iDisc to learn those patterns with internal discretized representations. The method implicitly partitions the scene into a set of high-level patterns. In particular, our new module, Internal Discretization (ID), implements a continuous-discrete-continuous bottleneck to learn those concepts without supervision. In contrast to state-of-the-art methods, the proposed model does not enforce any explicit constraints or priors on the depth output. The whole network with the ID module can be trained end-to-end, thanks to the bottleneck module based on attention. Our method sets the new state of the art with significant improvements on NYU-Depth v2 and KITTI, outperforming all published methods on the official KITTI benchmark. iDisc can also achieve state-of-the-art results on surface normal estimation. Further, we explore the model generalization capability via zero-shot testing. We observe the compelling need to promote diversification in the outdoor scenario. Hence, we introduce splits of two autonomous driving datasets, DDAD and Argoverse. Code is available at http://vis.xyz/pub/idisc .