# MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

arXiv: https://arxiv.org/abs/2607.27616 · HTML: https://mlsanity.com/paper/2607.27616/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 45 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 30 of 35)

- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [ImgEdit: A Unified Image Editing Dataset and Benchmark](https://mlsanity.com/paper/2505.20275/) (2025)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation](https://mlsanity.com/paper/2406.16855/) (2024)
- [Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot](https://mlsanity.com/paper/2402.14654/) (2024)
- [ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling](https://mlsanity.com/paper/2501.02487/) (2025)
- [DreamO: A Unified Framework for Image Customization](https://mlsanity.com/paper/2504.16915/) (2025)
- [Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions](https://mlsanity.com/paper/2410.20294/) (2024)
- [HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance](https://mlsanity.com/paper/2407.06937/) (2024)
- [Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset](https://mlsanity.com/paper/2506.18851/) (2025)
- [WithAnyone: Towards Controllable and ID Consistent Image Generation](https://mlsanity.com/paper/2510.14975/) (2025)
- [Reconstructing Three-Dimensional Models of Interacting Humans](https://mlsanity.com/paper/2308.01854/) (2023)
- [GEditBench v2: A Human-Aligned Benchmark for General Image Editing](https://mlsanity.com/paper/2603.28547/) (2026)
- [PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards](https://mlsanity.com/paper/2512.01236/) (2025)
- [MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans](https://mlsanity.com/paper/2506.20879/) (2025)
- [CondiMen: Conditional Multi-Person Mesh Recovery](https://mlsanity.com/paper/2412.13058/) (2024)
- [SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation](https://mlsanity.com/paper/2510.06469/) (2025)
- [Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space](https://mlsanity.com/paper/2511.13282/) (2025)
- [GroupDiff: Diffusion-based Group Portrait Editing](https://mlsanity.com/paper/2409.14379/) (2024)
- [BodyMetric: Evaluating the Realism of Human Bodies in Text-to-Image Generation](https://mlsanity.com/paper/2412.04086/) (2024)
- [MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation](https://mlsanity.com/paper/2607.01383/) (2026)
- [gDist: Efficient Distance Computation between 3D Meshes on GPU](https://mlsanity.com/paper/2411.11244/) (2024)
- [SkeleGuide: Explicit Skeleton Reasoning for Context-Aware Human-in-Place Image Synthesis](https://mlsanity.com/paper/2603.01579/) (2026)

## Built on by (most cited first, 1 of 1)

- [Human-Centric Intelligence in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2608.18184/) (2026)

## Abstract (arXiv)

Text-to-image and personalized editing models now synthesize high-fidelity single-subject images with ease. Yet placing multiple named people into shared contact actions such as embrace, carry, or grapple still exposes major failures: fused limbs, invented extremities, and interpenetrating bodies. Existing evaluations largely overlook these anatomical and geometric issues, and VLM-as-a-judge checklists often saturate on Interaction while the errors remain obvious to humans. We introduce MPIE-Bench, a 2,500-sample benchmark of video-mined editing triplets spanning 405 scenes, 14 interaction categories, and four contact densities (C0-C3). We also propose MPIE-Eval, whose two new axes score contact-time geometry from a frozen public multi-person mesh reconstruction. Anatomy asks whether every human-like mass is explained by a complete set of reconstructed bodies, and Interaction asks whether the penetration and surface distance between those bodies match the contact the instruction asked for. Across ten editors, mesh Anatomy tops out at 0.65 and mesh Interaction at 0.72 on two different models, so no single editor is strong on both, while VLM checklists rate the same images above 0.95. A five-rater study confirms that both axes track human judgement more closely than a zero-shot VLM judge, and the rankings hold under ablation of every weight and threshold.