# PICABench: How Far Are We from Physically Realistic Image Editing?

arXiv: https://arxiv.org/abs/2510.17681 · HTML: https://mlsanity.com/paper/2510.17681/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 46 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 30 of 38)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [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)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea](https://mlsanity.com/paper/2411.15738/) (2024)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [ImgEdit: A Unified Image Editing Dataset and Benchmark](https://mlsanity.com/paper/2505.20275/) (2025)
- [WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2503.07265/) (2025)
- [SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models](https://mlsanity.com/paper/2312.06739/) (2023)
- [MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions](https://mlsanity.com/paper/2407.06358/) (2024)
- [HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer](https://mlsanity.com/paper/2505.22705/) (2025)
- [AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark](https://mlsanity.com/paper/2410.03051/) (2024)
- [UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics](https://mlsanity.com/paper/2412.07774/) (2024)
- [Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation](https://mlsanity.com/paper/2508.09987/) (2025)
- [Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing](https://mlsanity.com/paper/2504.02826/) (2025)
- [Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding](https://mlsanity.com/paper/2510.06308/) (2025)
- [Effective Real Image Editing with Accelerated Iterative Diffusion Inversion](https://mlsanity.com/paper/2309.04907/) (2023)
- [KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models](https://mlsanity.com/paper/2505.16707/) (2025)
- [VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection](https://mlsanity.com/paper/2411.14794/) (2024)
- [I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing](https://mlsanity.com/paper/2408.14180/) (2024)
- [EditWorld: Simulating World Dynamics for Instruction-Following Image Editing](https://mlsanity.com/paper/2405.14785/) (2024)
- [T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation](https://mlsanity.com/paper/2508.17472/) (2025)
- [Learning Action and Reasoning-Centric Image Editing from Videos and Simulations](https://mlsanity.com/paper/2407.03471/) (2024)

## Built on by (most cited first, 16 of 16)

- [RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time](https://mlsanity.com/paper/2604.11626/) (2026)
- [Quantifying the Gap between Understanding and Generation within Unified Multimodal Models](https://mlsanity.com/paper/2602.02140/) (2026)
- [Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework](https://mlsanity.com/paper/2606.19073/) (2026)
- [From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors](https://mlsanity.com/paper/2602.21778/) (2026)
- [ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?](https://mlsanity.com/paper/2603.25823/) (2026)
- [Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions](https://mlsanity.com/paper/2604.15917/) (2026)
- [Do Image Editing Models Understand Lighting?](https://mlsanity.com/paper/2606.26738/) (2026)
- [Do-Undo Bench: Reversibility for Action Understanding in Image Generation](https://mlsanity.com/paper/2512.13609/) (2025)
- [DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents](https://mlsanity.com/paper/2605.01789/) (2026)
- [LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation](https://mlsanity.com/paper/2605.07640/) (2026)
- [Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis](https://mlsanity.com/paper/2605.14842/) (2026)
- [Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning](https://mlsanity.com/paper/2606.24548/) (2026)
- [TransPhy: Visual In-Context Learning for Physically Grounded Image Editing](https://mlsanity.com/paper/2608.24119/) (2026)
- [PAWBench: How Far Are We from Probabilistically Aligned World Modeling?](https://mlsanity.com/paper/2608.27345/) (2026)
- [Evaluating the Evaluators: Diagnosing Large Multimodal Models for AI-Generated Image Assessment](https://mlsanity.com/paper/2609.37576/) (2026)
- [Do Image Editors Follow Depth-Dependent Blur and Aperture Response? A Rendered-Ground-Truth Pilot Audit](https://mlsanity.com/paper/2610.09344/) (2026)

## Abstract (arXiv)

Image editing has achieved remarkable progress recently. Modern editing models could already follow complex instructions to manipulate the original content. However, beyond completing the editing instructions, the accompanying physical effects are the key to the generation realism. For example, removing an object should also remove its shadow, reflections, and interactions with nearby objects. Unfortunately, existing models and benchmarks mainly focus on instruction completion but overlook these physical effects. So, at this moment, how far are we from physically realistic image editing? To answer this, we introduce PICABench, which systematically evaluates physical realism across eight sub-dimension (spanning optics, mechanics, and state transitions) for most of the common editing operations (add, remove, attribute change, etc.). We further propose the PICAEval, a reliable evaluation protocol that uses VLM-as-a-judge with per-case, region-level human annotations and questions. Beyond benchmarking, we also explore effective solutions by learning physics from videos and construct a training dataset PICA-100K. After evaluating most of the mainstream models, we observe that physical realism remains a challenging problem with large rooms to explore. We hope that our benchmark and proposed solutions can serve as a foundation for future work moving from naive content editing toward physically consistent realism.