Generating Fine Details of Entity Interactions

• URL: http://arxiv.org/abs/2504.08714v1
• Date: Fri, 11 Apr 2025 17:24:58 GMT
• Title: Generating Fine Details of Entity Interactions
• Authors: Xinyi Gu, Jiayuan Mao,
• Abstract summary: This paper introduces InterActing, an interaction-focused dataset with 1000 fine-grained prompts covering three key scenarios.<n>We propose a decomposition-augmented refinement procedure to address interaction generation challenges.<n>Our approach, DetailScribe, uses a VLM to critique generated images, and applies targeted interventions within the diffusion process in refinement.
• Score: 17.130839907951877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Images not only depict objects but also encapsulate rich interactions between them. However, generating faithful and high-fidelity images involving multiple entities interacting with each other, is a long-standing challenge. While pre-trained text-to-image models are trained on large-scale datasets to follow diverse text instructions, they struggle to generate accurate interactions, likely due to the scarcity of training data for uncommon object interactions. This paper introduces InterActing, an interaction-focused dataset with 1000 fine-grained prompts covering three key scenarios: (1) functional and action-based interactions, (2) compositional spatial relationships, and (3) multi-subject interactions. To address interaction generation challenges, we propose a decomposition-augmented refinement procedure. Our approach, DetailScribe, built on Stable Diffusion 3.5, leverages LLMs to decompose interactions into finer-grained concepts, uses a VLM to critique generated images, and applies targeted interventions within the diffusion process in refinement. Automatic and human evaluations show significantly improved image quality, demonstrating the potential of enhanced inference strategies. Our dataset and code are available at https://concepts-ai.com/p/detailscribe/ to facilitate future exploration of interaction-rich image generation.

Related papers

• Visual-Geometric Collaborative Guidance for Affordance Learning [63.038406948791454]
  We propose a visual-geometric collaborative guided affordance learning network that incorporates visual and geometric cues. Our method outperforms the representative models regarding objective metrics and visual quality.
  arXiv  Detail & Related papers  (2024-10-15T07:35:51Z)
• HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding [8.10024991952397]
  Existing methods focus on complex interactivities while leveraging a simple relationship model. We propose a new approach named Hierarchical Interlacement Graph (HIG), which leverages a unified layer and graph within a hierarchical structure. Our approach demonstrates superior performance to other methods through extensive experiments conducted in various scenarios.
  arXiv  Detail & Related papers  (2023-12-05T18:47:19Z)
• MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts [92.76662894585809]
  We introduce an approach to enhance multimodal models, which we call Multimodal Mixtures of Experts (MMoE) MMoE is able to be applied to various types of models to gain improvement.
  arXiv  Detail & Related papers  (2023-11-16T05:31:21Z)
• InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion [29.25063155767897]
  This paper addresses a novel task of anticipating 3D human-object interactions (HOIs) Our task is significantly more challenging, as it requires modeling dynamic objects with various shapes, capturing whole-body motion, and ensuring physically valid interactions. Experiments on multiple human-object interaction datasets demonstrate the effectiveness of our method for this task, capable of producing realistic, vivid, and remarkably long-term 3D HOI predictions.
  arXiv  Detail & Related papers  (2023-08-31T17:59:08Z)
• Mutual Information-driven Triple Interaction Network for Efficient Image Dehazing [54.168567276280505]
  We propose a novel Mutual Information-driven Triple interaction Network (MITNet) for image dehazing. The first stage, named amplitude-guided haze removal, aims to recover the amplitude spectrum of the hazy images for haze removal. The second stage, named phase-guided structure refined, devotes to learning the transformation and refinement of the phase spectrum.
  arXiv  Detail & Related papers  (2023-08-14T08:23:58Z)
• Feature Decoupling-Recycling Network for Fast Interactive Segmentation [79.22497777645806]
  Recent interactive segmentation methods iteratively take source image, user guidance and previously predicted mask as the input. We propose the Feature Decoupling-Recycling Network (FDRN), which decouples the modeling components based on their intrinsic discrepancies.
  arXiv  Detail & Related papers  (2023-08-07T12:26:34Z)
• Improving Human-Object Interaction Detection via Virtual Image Learning [68.56682347374422]
  Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects. In this paper, we propose to alleviate the impact of such an unbalanced distribution via Virtual Image Leaning (VIL) A novel label-to-image approach, Multiple Steps Image Creation (MUSIC), is proposed to create a high-quality dataset that has a consistent distribution with real images.
  arXiv  Detail & Related papers  (2023-08-04T10:28:48Z)
• Multi-Grained Multimodal Interaction Network for Entity Linking [65.30260033700338]
  Multimodal entity linking task aims at resolving ambiguous mentions to a multimodal knowledge graph. We propose a novel Multi-GraIned Multimodal InteraCtion Network $textbf(MIMIC)$ framework for solving the MEL task.
  arXiv  Detail & Related papers  (2023-07-19T02:11:19Z)
• Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition [8.513434732050749]
  We propose an Interactive Spatiotemporal Token Attention Network (ISTA-Net), which simultaneously model spatial, temporal, and interactive relations. Our network contains a tokenizer to partition Interactive Spatiotemporal Tokens (ISTs), which is a unified way to represent motions of multiple diverse entities. To jointly learn along three dimensions in ISTs, multi-head self-attention blocks integrated with 3D convolutions are designed to capture inter-token correlations.
  arXiv  Detail & Related papers  (2023-07-14T16:51:25Z)
• Effective Actor-centric Human-object Interaction Detection [20.564689533862524]
  We propose a novel actor-centric framework to detect Human-Object Interaction in images. Our method achieves the state-of-the-art on the challenging V-COCO and HICO-DET benchmarks.
  arXiv  Detail & Related papers  (2022-02-24T10:24:44Z)
• Information Interaction Profile of Choice Adoption [2.9972063833424216]
  We introduce an efficient method to infer the entities interaction network and its evolution according to the temporal distance separating interacting entities. The interaction profile allows characterizing the mechanisms of the interaction processes. We show that the effect of a combination of exposures on a user is more than the sum of each exposure's independent effect--there is an interaction.
  arXiv  Detail & Related papers  (2021-04-28T10:42:25Z)
• Cascaded Human-Object Interaction Recognition [175.60439054047043]
  We introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding.
  arXiv  Detail & Related papers  (2020-03-09T17:05:04Z)

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.