# Object-Driven Multi-Layer Scene Decomposition From a Single Image

arXiv: https://arxiv.org/abs/1908.09521 · HTML: https://mlsanity.com/paper/1908.09521/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2019.

## Built on by (most cited first, 26 of 26)

- [Behind the Scenes: Density Fields for Single View Reconstruction](https://mlsanity.com/paper/2301.07668/) (2023)
- [Amodal Ground Truth and Completion in the Wild](https://mlsanity.com/paper/2312.17247/) (2023)
- [Amodal Completion via Progressive Mixed Context Diffusion](https://mlsanity.com/paper/2312.15540/) (2023)
- [MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation](https://mlsanity.com/paper/2404.02790/) (2024)
- [Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition](https://mlsanity.com/paper/2104.05367/) (2021)
- [From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction](https://mlsanity.com/paper/2203.08122/) (2022)
- [Open-World Amodal Appearance Completion](https://mlsanity.com/paper/2411.13019/) (2024)
- [Image Amodal Completion: A Survey](https://mlsanity.com/paper/2207.02062/) (2022)
- [Decoupling Dynamic Monocular Videos for Dynamic View Synthesis](https://mlsanity.com/paper/2304.01716/) (2023)
- [Object-level Scene Deocclusion](https://mlsanity.com/paper/2406.07706/) (2024)
- [Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting](https://mlsanity.com/paper/2503.21770/) (2025)
- [BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion](https://mlsanity.com/paper/2401.01642/) (2024)
- [Chat2Map: Efficient Scene Mapping from Multi-Ego Conversations](https://mlsanity.com/paper/2301.02184/) (2023)
- [What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction](https://mlsanity.com/paper/2112.04481/) (2021)
- [Learning A Locally Unified 3D Point Cloud for View Synthesis](https://mlsanity.com/paper/2209.05013/) (2022)
- [Weakly But Deeply Supervised Occlusion-Reasoned Parametric Road Layouts](https://mlsanity.com/paper/2104.06730/) (2021)
- [Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA](https://mlsanity.com/paper/2503.10225/) (2025)
- [Referring Layer Decomposition](https://mlsanity.com/paper/2602.19358/) (2026)
- [Object-aware Monocular Depth Prediction with Instance Convolutions](https://mlsanity.com/paper/2112.01521/) (2021)
- [SynergyAmodal: Deocclude Anything with Text Control](https://mlsanity.com/paper/2504.19506/) (2025)
- [SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes](https://mlsanity.com/paper/2307.07333/) (2023)
- [CObL: Toward Zero-Shot Ordinal Layering without User Prompting](https://mlsanity.com/paper/2508.08498/) (2025)
- [Stable Diffusion-Based Approach for Human De-Occlusion](https://mlsanity.com/paper/2508.12663/) (2025)
- [PHAC: Promptable Human Amodal Completion](https://mlsanity.com/paper/2603.14741/) (2026)
- [SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons](https://mlsanity.com/paper/2603.24039/) (2026)
- [Integrating Multimodal Large Language Model Knowledge into Amodal Completion](https://mlsanity.com/paper/2603.28333/) (2026)

## Abstract (arXiv)

We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation that arranges the scene in layers, including originally occluded regions. Unlike previous work, we enable an adaptive scheme for the number of layers and incorporate semantic encoding for better hallucination of partly occluded objects. Additionally, our approach is object-driven, which especially boosts the accuracy for the occluded intermediate objects. The framework consists of two steps. First, we individually complete each object in terms of color and depth, while estimating the scene layout. Second, we rebuild the scene based on the regressed layers and enforce the recomposed image to resemble the structure of the original input. The learned representation enables various applications, such as 3D photography and diminished reality, all from a single RGB image.