SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation

• URL: http://arxiv.org/abs/2603.22228v1
• Date: Mon, 23 Mar 2026 17:26:35 GMT
• Title: SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation
• Abstract summary: We present textbfSpatialReward, a verifiable reward model explicitly designed to evaluate spatial layouts in generated images.<n>Experiments on Stable Diffusion and FLUX show that incorporating SpatialReward into RL training consistently improves spatial consistency and overall generation quality.
• Score: 62.55421542903781
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to fine-grained spatial relationships, often producing images that appear plausible overall yet contain inaccuracies in object positioning. In this work, we present \textbf{SpatialReward}, a verifiable reward model explicitly designed to evaluate spatial layouts in generated images. SpatialReward adopts a multi-stage pipeline: a \emph{Prompt Decomposer} extracts entities, attributes, and spatial metadata from free-form prompts; expert detectors provide accurate visual grounding of object positions and attributes; and a vision-language model applies chain-of-thought reasoning over grounded observations to assess complex spatial relations that are challenging for rule-based methods. To more comprehensively evaluate spatial relationships in generated images, we introduce \textbf{SpatRelBench}, a benchmark covering object attributes, orientation, inter-object relations, and rendered text placement. Experiments on Stable Diffusion and FLUX show that incorporating SpatialReward into RL training consistently improves spatial consistency and overall generation quality, with results aligned more closely to human judgments. These findings indicate that verifiable reward models hold considerable potential for enabling more accurate and controllable optimization in text-to-image generation models.

Related papers

• Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text [19.512871070260477]
  spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world.<n>Existing spatial reasoning benchmarks usually require coordinates, options, or text, creating an answer-interface mismatch for image-generation models.<n>We propose ProVisE, a benchmark-agnostic framework that elicits protocol-constrained visual answers from image-generation models.
  arXiv  Detail & Related papers  (2026-07-23T09:04:48Z)
• Enhancing Spatial Understanding in Image Generation via Reward Modeling [23.754373024995132]
  We introduce a novel method that strengthens the spatial understanding of current image generation models.<n>We build SpatialScore, a reward model designed to evaluate the accuracy of spatial relationships in text-to-image generation.
  arXiv  Detail & Related papers  (2026-02-27T17:59:57Z)
• RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection [18.52946282633359]
  RL-RIG is a Reinforcement Learning framework for Reflection-based Image Generation.<n>We develop Reflection-GRPO to train the VLM Actor for edit prompts and the Image Editor for better image quality under a given prompt.<n> Experimental results show that RL-RIG outperforms existing state-of-the-art open-source models by up to 11% in terms of controllable and precise spatial reasoning in image generation.
  arXiv  Detail & Related papers  (2026-02-23T15:39:53Z)
• Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models [3.5999252362400993]
  A prevalent issue in compositional generation is the misalignment of spatial relationships.<n>We introduce a novel evaluation metric designed to assess the alignment of 2D and 3D spatial relationships between text and image.<n>We also propose PoS-based Generation, an inference-time method that improves the alignment of 2D and 3D spatial relationships in T2I models without requiring fine-tuning.
  arXiv  Detail & Related papers  (2025-06-29T22:41:27Z)
• Exploring the latent space of diffusion models directly through singular value decomposition [31.900933527692846]
  We propose a novel image editing framework that is capable of learning arbitrary attributes from one pair of latent codes destined by text prompts in Diffusion Models.<n>We will release our codes soon to foster further research and applications in this area.
  arXiv  Detail & Related papers  (2025-02-04T11:04:36Z)
• REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models [67.55362046790512]
  Vision-language models lack the ability to correctly reason over spatial relationships. We develop the REVISION framework which improves spatial fidelity in vision-language models. Our results and findings indicate that utilizing rendering-based frameworks is an effective approach for developing spatially-aware models.
  arXiv  Detail & Related papers  (2024-08-05T04:51:46Z)
• Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities [88.398085358514]
  Contrastive Deepfake Embeddings (CoDE) is a novel embedding space specifically designed for deepfake detection. CoDE is trained via contrastive learning by additionally enforcing global-local similarities.
  arXiv  Detail & Related papers  (2024-07-29T18:00:10Z)
• SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation [68.42476385214785]
  We propose a novel Spatial-Semantic Map Guided (SSMG) diffusion model that adopts the feature map, derived from the layout, as guidance. SSMG achieves superior generation quality with sufficient spatial and semantic controllability compared to previous works. We also propose the Relation-Sensitive Attention (RSA) and Location-Sensitive Attention (LSA) mechanisms.
  arXiv  Detail & Related papers  (2023-08-20T04:09:12Z)
• Benchmarking Spatial Relationships in Text-to-Image Generation [102.62422723894232]
  We investigate the ability of text-to-image models to generate correct spatial relationships among objects. We present VISOR, an evaluation metric that captures how accurately the spatial relationship described in text is generated in the image. Our experiments reveal a surprising finding that, although state-of-the-art T2I models exhibit high image quality, they are severely limited in their ability to generate multiple objects or the specified spatial relations between them.
  arXiv  Detail & Related papers  (2022-12-20T06:03:51Z)
• Salient Objects in Clutter [130.63976772770368]
  This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets. This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets. We propose a new high-quality dataset and update the previous saliency benchmark.
  arXiv  Detail & Related papers  (2021-05-07T03:49:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.