# Background Prompting for Improved Object Depth

arXiv: https://arxiv.org/abs/2306.05428 · HTML: https://mlsanity.com/paper/2306.05428/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 30 of 35)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [Exploring Visual Prompts for Adapting Large-Scale Models](https://mlsanity.com/paper/2203.17274/) (2022)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [Learning to Recover 3D Scene Shape from a Single Image](https://mlsanity.com/paper/2012.09365/) (2020)
- [3D Photography using Context-aware Layered Depth Inpainting](https://mlsanity.com/paper/2004.04727/) (2020)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation](https://mlsanity.com/paper/2204.00987/) (2022)
- [Learning the Depths of Moving People by Watching Frozen People](https://mlsanity.com/paper/1904.11111/) (2019)
- [BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration](https://mlsanity.com/paper/1604.01093/) (2016)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [Unsupervised Monocular Depth Learning in Dynamic Scenes](https://mlsanity.com/paper/2010.16404/) (2020)
- [How do neural networks see depth in single images?](https://mlsanity.com/paper/1905.07005/) (2019)

## Built on by (most cited first, 2 of 2)

- [StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal](https://mlsanity.com/paper/2406.16864/) (2024)
- [Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion](https://mlsanity.com/paper/2412.09593/) (2024)

## Abstract (arXiv)

Estimating the depth of objects from a single image is a valuable task for many vision, robotics, and graphics applications. However, current methods often fail to produce accurate depth for objects in diverse scenes. In this work, we propose a simple yet effective Background Prompting strategy that adapts the input object image with a learned background. We learn the background prompts only using small-scale synthetic object datasets. To infer object depth on a real image, we place the segmented object into the learned background prompt and run off-the-shelf depth networks. Background Prompting helps the depth networks focus on the foreground object, as they are made invariant to background variations. Moreover, Background Prompting minimizes the domain gap between synthetic and real object images, leading to better sim2real generalization than simple finetuning. Results on multiple synthetic and real datasets demonstrate consistent improvements in real object depths for a variety of existing depth networks. Code and optimized background prompts can be found at: https://mbaradad.github.io/depth_prompt.