# Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance

arXiv: https://arxiv.org/abs/2509.17757 · HTML: https://mlsanity.com/paper/2509.17757/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Training-Free Consistent Text-to-Image Generation](https://mlsanity.com/paper/2402.03286/) (2024)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [SeGAN: Segmenting and Generating the Invisible](https://mlsanity.com/paper/1703.10239/) (2017)
- [Amodal Completion via Progressive Mixed Context Diffusion](https://mlsanity.com/paper/2312.15540/) (2023)
- [Text2Layer: Layered Image Generation using Latent Diffusion Model](https://mlsanity.com/paper/2307.09781/) (2023)
- [LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation](https://mlsanity.com/paper/1703.01560/) (2017)
- [Human De-occlusion: Invisible Perception and Recovery for Humans](https://mlsanity.com/paper/2103.11597/) (2021)
- [Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery](https://mlsanity.com/paper/1907.09381/) (2019)
- [Alfie: Democratising RGBA Image Generation With No ](https://mlsanity.com/paper/2408.14826/) (2024)
- [LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors](https://mlsanity.com/paper/2412.04460/) (2024)
- [Generating Compositional Scenes via Text-to-image RGBA Instance Generation](https://mlsanity.com/paper/2411.10913/) (2024)

## Built on by (most cited first, 3 of 3)

- [GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence](https://mlsanity.com/paper/2511.21945/) (2025)
- [Object Counting with GPT-4o and GPT-5: A Comparative Study](https://mlsanity.com/paper/2512.03233/) (2025)
- [Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation](https://mlsanity.com/paper/2512.20936/) (2025)

## Abstract (arXiv)

Amodal completion, generating invisible parts of occluded objects, is vital for applications like image editing and AR. Prior methods face challenges with data needs, generalization, or error accumulation in progressive pipelines. We propose a Collaborative Multi-Agent Reasoning Framework based on upfront collaborative reasoning to overcome these issues. Our framework uses multiple agents to collaboratively analyze occlusion relationships and determine necessary boundary expansion, yielding a precise mask for inpainting. Concurrently, an agent generates fine-grained textual descriptions, enabling Fine-Grained Semantic Guidance. This ensures accurate object synthesis and prevents the regeneration of occluders or other unwanted elements, especially within large inpainting areas. Furthermore, our method directly produces layered RGBA outputs guided by visible masks and attention maps from a Diffusion Transformer, eliminating extra segmentation. Extensive evaluations demonstrate our framework achieves state-of-the-art visual quality.