# Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA

arXiv: https://arxiv.org/abs/2503.10225 · HTML: https://mlsanity.com/paper/2503.10225/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 54 of its 77 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 54)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [PixelLM: Pixel Reasoning with Large Multimodal Model](https://mlsanity.com/paper/2312.02228/) (2023)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [GSVA: Generalized Segmentation via Multimodal Large Language Models](https://mlsanity.com/paper/2312.10103/) (2023)
- [OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding](https://mlsanity.com/paper/2406.19389/) (2024)
- [VISA: Reasoning Video Object Segmentation via Large Language Models](https://mlsanity.com/paper/2407.11325/) (2024)
- [Semantic Amodal Segmentation](https://mlsanity.com/paper/1509.01329/) (2015)
- [PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model](https://mlsanity.com/paper/2403.14598/) (2024)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [Amodal Instance Segmentation](https://mlsanity.com/paper/1604.08202/) (2016)
- [Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation](https://mlsanity.com/paper/1804.08864/) (2018)
- [SeGAN: Segmenting and Generating the Invisible](https://mlsanity.com/paper/1703.10239/) (2017)
- [LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning](https://mlsanity.com/paper/2404.08767/) (2024)
- [Amodal Ground Truth and Completion in the Wild](https://mlsanity.com/paper/2312.17247/) (2023)

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

- [Shape Distribution Matters: Shape-specific Mixture-of-Experts for Amodal Segmentation under Diverse Occlusions](https://mlsanity.com/paper/2508.01664/) (2025)
- [R2SM: Referring and Reasoning for Selective Masks](https://mlsanity.com/paper/2506.01795/) (2025)
- [Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation](https://mlsanity.com/paper/2508.01661/) (2025)

## Abstract (arXiv)

Amodal segmentation aims to infer the complete shape of occluded objects, even when the occluded region's appearance is unavailable. However, current amodal segmentation methods lack the capability to interact with users through text input and struggle to understand or reason about implicit and complex purposes. While methods like LISA integrate multi-modal large language models (LLMs) with segmentation for reasoning tasks, they are limited to predicting only visible object regions and face challenges in handling complex occlusion scenarios. To address these limitations, we propose a novel task named amodal reasoning segmentation, aiming to predict the complete amodal shape of occluded objects while providing answers with elaborations based on user text input. We develop a generalizable dataset generation pipeline and introduce a new dataset focusing on daily life scenarios, encompassing diverse real-world occlusions. Furthermore, we present AURA (Amodal Understanding and Reasoning Assistant), a novel model with advanced global and spatial-level designs specifically tailored to handle complex occlusions. Extensive experiments validate AURA's effectiveness on the proposed dataset.