# Integrating Multimodal Large Language Model Knowledge into Amodal Completion

arXiv: https://arxiv.org/abs/2603.28333 · HTML: https://mlsanity.com/paper/2603.28333/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Semantic Amodal Segmentation](https://mlsanity.com/paper/1509.01329/) (2015)
- [Fine-Grained Visual Prompting](https://mlsanity.com/paper/2306.04356/) (2023)
- [pix2gestalt: Amodal Segmentation by Synthesizing Wholes](https://mlsanity.com/paper/2401.14398/) (2024)
- [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)
- [Human De-occlusion: Invisible Perception and Recovery for Humans](https://mlsanity.com/paper/2103.11597/) (2021)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [Object-Driven Multi-Layer Scene Decomposition From a Single Image](https://mlsanity.com/paper/1908.09521/) (2019)
- [Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery](https://mlsanity.com/paper/1907.09381/) (2019)
- [A Tri-Layer Plugin to Improve Occluded Detection](https://mlsanity.com/paper/2210.10046/) (2022)
- [Open-World Amodal Appearance Completion](https://mlsanity.com/paper/2411.13019/) (2024)
- [Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models](https://mlsanity.com/paper/2404.04514/) (2024)

## Abstract (arXiv)

With the widespread adoption of autonomous vehicles and robotics, amodal completion, which reconstructs the occluded parts of people and objects in an image, has become increasingly crucial. Just as humans infer hidden regions based on prior experience and common sense, this task inherently requires physical knowledge about real-world entities. However, existing approaches either depend solely on the image generation ability of visual generative models, which lack such knowledge, or leverage it only during the segmentation stage, preventing it from explicitly guiding the completion process. To address this, we propose AmodalCG, a novel framework that harnesses the real-world knowledge of Multimodal Large Language Models (MLLMs) to guide amodal completion. Our framework first assesses the extent of occlusion to selectively invoke MLLM guidance only when the target object is heavily occluded. If guidance is required, the framework further incorporates MLLMs to reason about both the (1) extent and (2) content of the missing regions. Finally, a visual generative model integrates these guidance and iteratively refines imperfect completions that may arise from inaccurate MLLM guidance. Experimental results on various real-world images show impressive improvements compared to all existing works, suggesting MLLMs as a promising direction for addressing challenging amodal completion.