# POCI-Diff: 3D-Layout Guided Diffusion for Controllable Synthetic Surveillance Data Generation

arXiv: https://arxiv.org/abs/2601.14056 · HTML: https://mlsanity.com/paper/2601.14056/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 20 Jan 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, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion](https://mlsanity.com/paper/2307.10816/) (2023)
- [Real-Time Flying Object Detection with YOLOv8](https://mlsanity.com/paper/2305.09972/) (2023)
- [ARNIQA: Learning Distortion Manifold for Image Quality Assessment](https://mlsanity.com/paper/2310.14918/) (2023)
- [LooseControl: Lifting ControlNet for Generalized Depth Conditioning](https://mlsanity.com/paper/2312.03079/) (2023)
- [Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation](https://mlsanity.com/paper/2408.14819/) (2024)
- [Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training](https://mlsanity.com/paper/2406.06045/) (2024)
- [Diffusion-based Synthetic Data Generation for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2503.12472/) (2025)
- [Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian Detection](https://mlsanity.com/paper/2305.09401/) (2023)
- [ESPLoRA: Enhanced Spatial Precision with Low-Rank Adaption in Text-to-Image Diffusion Models for High-Definition Synthesis](https://mlsanity.com/paper/2504.13745/) (2025)

## Built on by (most cited first, 2 of 2)

- [Clustering-Enhanced Domain Adaptation for Cross-Domain Intrusion Detection in Industrial Control Systems](https://mlsanity.com/paper/2604.12183/) (2026)
- [Medoid Prototype Alignment for Cross-Plant Unknown Attack Detection in Industrial Control Systems](https://mlsanity.com/paper/2604.25544/) (2026)

## Abstract (arXiv)

Training robust visual surveillance models requires large-scale datasets with precise spatial annotations, yet collecting real surveillance data is costly, privacy-sensitive, and often legally constrained. Synthetic data generation offers a compelling alternative, but existing methods lack fine-grained 3D control over object placement and appearance, limiting geometric consistency across camera viewpoints. We introduce POCI-Diff (Positioning Objects Consistently and Interactively), a framework that generates annotated synthetic scenes from explicit 3D bounding-box layouts with per-object semantic control. By integrating Blended Latent Diffusion with depth-conditioned ControlNet, POCI-Diff synthesises complex multi-object scenes in a single forward pass, binding individual text descriptions to specific 3D locations. We further propose a warping-free editing pipeline supporting object insertion, removal, and transformation via regeneration, enabling efficient scene variation for data augmentation. Object identity across edits is preserved by conditioning on reference images via IP-Adapter, ensuring appearance consistency throughout interactive scene manipulation. Experiments show that POCI-Diff outperforms state-of-the-art 3D layout-guided generation methods in visual fidelity and layout adherence, while eliminating warping-induced geometric artifacts.