# PHAC: Promptable Human Amodal Completion

arXiv: https://arxiv.org/abs/2603.14741 · HTML: https://mlsanity.com/paper/2603.14741/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 55 of its 73 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 55)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [Deformable GANs for Pose-based Human Image Generation](https://mlsanity.com/paper/1801.00055/) (2017)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Person Image Synthesis via Denoising Diffusion Model](https://mlsanity.com/paper/2211.12500/) (2022)
- [Semantic Amodal Segmentation](https://mlsanity.com/paper/1509.01329/) (2015)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [PEEKABOO: Interactive Video Generation via Masked-Diffusion](https://mlsanity.com/paper/2312.07509/) (2023)
- [PromptHMR: Promptable Human Mesh Recovery](https://mlsanity.com/paper/2504.06397/) (2025)
- [SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion](https://mlsanity.com/paper/2311.15855/) (2023)
- [pix2gestalt: Amodal Segmentation by Synthesizing Wholes](https://mlsanity.com/paper/2401.14398/) (2024)
- [Exploring Dual-task Correlation for Pose Guided Person Image Generation](https://mlsanity.com/paper/2203.02910/) (2022)

## Abstract (arXiv)

Conditional image generation methods are increasingly used in human-centric applications, yet existing human amodal completion (HAC) models offer users limited control over the completed content. Given an occluded person image, they hallucinate invisible regions while preserving visible ones, but cannot reliably incorporate user-specified constraints such as a desired pose or spatial extent. As a result, users often resort to repeatedly sampling the model until they obtain a satisfactory output. Pose-guided person image synthesis (PGPIS) methods allow explicit pose conditioning, but frequently fail to preserve the instance-specific visible appearance and tend to be biased toward the training distribution, even when built on strong diffusion model priors. To address these limitations, we introduce promptable human amodal completion (PHAC), a new task that completes occluded human images while satisfying both visible appearance constraints and multiple user prompts. Users provide simple point-based prompts, such as additional joints for the target pose or bounding boxes for desired regions; these prompts are encoded using ControlNet modules specialized for each prompt type. These modules inject the prompt signals into a pre-trained diffusion model, and we fine-tune only the cross-attention blocks to obtain strong prompt alignment without degrading the underlying generative prior. To further preserve visible content, we propose an inpainting-based refinement module that starts from a slightly noised coarse completion, faithfully preserves the visible regions, and ensures seamless blending at occlusion boundaries. Extensive experiments on the HAC and PGPIS benchmarks show that our approach yields more physically plausible and higher-quality completions, while significantly improving prompt alignment compared with existing amodal completion and pose-guided synthesis methods.