Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning

• URL: http://arxiv.org/abs/2604.09850v1
• Date: Fri, 10 Apr 2026 19:25:24 GMT
• Title: Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning
• Abstract summary: Existing text-to-image diffusion models treat the background as a passive and under-optimized byproduct.<n>We propose a training-free framework that restructures diffusion sampling to explicitly account for foreground-background interactions.
• Score: 63.21130437262217
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized byproduct. This imbalance compromises global scene coherence and constrains compositional control. To address the limitation, we propose a training-free framework that restructures diffusion sampling to explicitly account for foreground-background interactions. Our approach consists of two key components. First, Dynamic Spatial Guidance introduces a soft, time step dependent gating mechanism that modulates foreground and background attention during the diffusion process, enabling spatially balanced generation. Second, Multi-Path Pruning performs multi-path latent exploration and dynamically filters candidate trajectories using both internal attention statistics and external semantic alignment signals, retaining trajectories that better satisfy object-background constraints. We further develop a benchmark specifically designed to evaluate object-background compositionality. Extensive evaluations across multiple diffusion backbones demonstrate consistent improvements in background coherence and object-background compositional alignment.

Related papers

• FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM [50.9765003472032]
  FoundationSLAM is a learning-based monocular dense SLAM system for accurate and robust tracking and mapping.<n>Our core idea is to bridge flow estimation with reasoning by leveraging the guidance from foundation depth models.
  arXiv  Detail & Related papers  (2025-12-31T17:57:45Z)
• Background Matters Too: A Language-Enhanced Adversarial Framework for Person Re-Identification [1.409283414986451]
  We argue that background semantics are as important as the foreground semantics in ReID.<n>This paper proposes an end-to-end framework that jointly models foreground and background information.
  arXiv  Detail & Related papers  (2025-09-03T05:38:22Z)
• FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus [10.615833390806486]
  Multi-subject personalized image generation aims to synthesize customized images containing multiple specified subjects without requiring test-time optimization.<n>We present FocusDPO, a framework that adaptively identifies focus regions based on dynamic semantic correspondence and supervision image complexity.
  arXiv  Detail & Related papers  (2025-09-01T07:06:36Z)
• DINTR: Tracking via Diffusion-based Interpolation [12.130669304428565]
  This work proposes a novel diffusion-based methodology to formulate the tracking task. Our INterpolation TrackeR (DINTR) presents a promising new paradigm and achieves a superior multiplicity on seven benchmarks across five indicator representations.
  arXiv  Detail & Related papers  (2024-10-14T00:41:58Z)
• TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimization [59.412236435627094]
  TALE is a training-free framework harnessing the generative capabilities of text-to-image diffusion models. We equip TALE with two mechanisms dubbed Adaptive Latent Manipulation and Energy-guided Latent Optimization. Our experiments demonstrate that TALE surpasses prior baselines and attains state-of-the-art performance in image-guided composition.
  arXiv  Detail & Related papers  (2024-08-07T08:52:21Z)
• Training-Free Semantic Video Composition via Pre-trained Diffusion Model [96.0168609879295]
  Current approaches, predominantly trained on videos with adjusted foreground color and lighting, struggle to address deep semantic disparities beyond superficial adjustments. We propose a training-free pipeline employing a pre-trained diffusion model imbued with semantic prior knowledge. Experimental results reveal that our pipeline successfully ensures the visual harmony and inter-frame coherence of the outputs.
  arXiv  Detail & Related papers  (2024-01-17T13:07:22Z)
• TivNe-SLAM: Dynamic Mapping and Tracking via Time-Varying Neural Radiance Fields [0.1227734309612871]
  This paper proposes a time-varying representation to track and reconstruct the dynamic scenes.<n>Two processes, a tracking process and a mapping process, are maintained simultaneously in our framework.<n>Experiments validate that our method achieves competitive results in both tracking and mapping when compared to existing state-of-the-art NeRF-based dynamic SLAM systems.
  arXiv  Detail & Related papers  (2023-10-29T06:10:46Z)
• Content-aware Warping for View Synthesis [110.54435867693203]
  We propose content-aware warping, which adaptively learns the weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network. Based on this learnable warping module, we propose a new end-to-end learning-based framework for novel view synthesis from two source views. Experimental results on structured light field datasets with wide baselines and unstructured multi-view datasets show that the proposed method significantly outperforms state-of-the-art methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2022-01-22T11:35:05Z)
• Deep Semantic Matching with Foreground Detection and Cycle-Consistency [103.22976097225457]
  We address weakly supervised semantic matching based on a deep network. We explicitly estimate the foreground regions to suppress the effect of background clutter. We develop cycle-consistent losses to enforce the predicted transformations across multiple images to be geometrically plausible and consistent.
  arXiv  Detail & Related papers  (2020-03-31T22:38:09Z)

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.