# GeoComposer: Geometry-Grounded Photographic Composition Instruction

arXiv: https://arxiv.org/abs/2609.26620 · HTML: https://mlsanity.com/paper/2609.26620/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 22 Sep 2026.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (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)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [Emu Edit: Precise Image Editing via Recognition and Generation Tasks](https://mlsanity.com/paper/2311.10089/) (2023)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [MEt3R: Measuring Multi-View Consistency in Generated Images](https://mlsanity.com/paper/2501.06336/) (2025)
- [What matters for Representation Alignment: Global Information or Spatial Structure?](https://mlsanity.com/paper/2512.10794/) (2025)
- [Grid Anchor based Image Cropping: A New Benchmark and An Efficient Model](https://mlsanity.com/paper/1909.08989/) (2019)
- [Emergent Outlier View Rejection in Visual Geometry Grounded Transformers](https://mlsanity.com/paper/2512.04012/) (2025)
- [Image Cropping with Composition and Saliency Aware Aesthetic Score Map](https://mlsanity.com/paper/1911.10492/) (2019)
- [PhotoFramer: Multi-modal Image Composition Instruction](https://mlsanity.com/paper/2512.00993/) (2025)
- [Towards Smart Point-and-Shoot Photography](https://mlsanity.com/paper/2505.03638/) (2025)
- [Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers](https://mlsanity.com/paper/2605.16949/) (2026)
- [CAPTAIN: Comprehensive Composition Assistance for Photo Taking](https://mlsanity.com/paper/1811.04184/) (2018)
- [Photography Perspective Composition: Towards Aesthetic Perspective Recommendation](https://mlsanity.com/paper/2505.20655/) (2025)
- [AesFormer: Transform Everyday Photos into Beautiful Memories](https://mlsanity.com/paper/2605.22126/) (2026)

## Abstract (arXiv)

Photographic composition aims to provide visual guidance for improving the framing, viewpoint, and spatial arrangement of an image. Early methods primarily rely on image cropping to enhance composition, which is restricted to the viewpoint and spatial arrangement of the input image. Recent methods have explored image understanding and editing to improve composition, but they mainly focus on instruction following and aesthetic quality, overlooking the importance of 3D scene geometry consistency for photographic composition. In this work, we propose GeoComposer, a novel geometry-grounded photographic composition framework that analyzes the composition of a given image to generate textual guidance and synthesizes a visual exemplar that enhances the composition of the given image. To promote geometry-grounded composition, we propose a geometry-aware representation learning mechanism that leverages geometric priors from a visual geometry foundation model to shape the intermediate representations of the composition editing model. This mechanism preserves both global structural relationships and local fine-grained correspondences for geometry-grounded composition. Furthermore, we propose a reinforcement learning strategy guided by a hybrid reward that jointly optimizes instruction following, aesthetic quality, and geometric consistency. This enables the model to generate visual exemplars that faithfully follow the composition instructions while remaining visually appealing and geometrically consistent. Extensive experiments show the superiority of our approach over state-of-the-art methods, highlighting its effectiveness in generating visually appealing and geometrically consistent composition.