paper-with-me

홈 › Papers

InpaintDPO: Mitigating Spatial Relationship Hallucinations in Foreground-conditioned Inpainting via Diverse Preference Optimization

2025-12-16 · Qirui Li, Yizhe Tang, Ran Yi, Guangben Lu, Fangyuan Zou, Peng Shu, Huan Yu, Jie Jiang arxiv

Foreground-conditioned inpainting, which aims at generating a harmonious background for a given foreground subject based on the text prompt, is an important subfield in controllable image generation. A common challenge in current methods, however, is the occurrence of Spatial Relationship Hallucinations between the foreground subject and the generated background, including inappropriate scale, positional relationships, and viewpoints. Critically, the subjective nature of spatial rationality makes it challenging to quantify, hindering the use of traditional reward-based RLHF methods. To address this issue, we propose InpaintDPO, the first Direct Preference Optimization (DPO) based framework dedicated to spatial rationality in foreground-conditioned inpainting, ensuring plausible spatial relationships between foreground and background elements. To resolve the gradient conflicts in standard DPO caused by identical foreground in win-lose pairs, we propose MaskDPO, which confines preference optimization exclusively to the background to enhance background spatial relationships, while retaining the inpainting loss in the foreground region for robust foreground preservation. To enhance coherence at the foreground-background boundary, we propose Conditional Asymmetric Preference Optimization, which samples pairs with differentiated cropping operations and applies global preference optimization to promote contextual awareness and enhance boundary coherence. Finally, based on the observation that winning samples share a commonality in plausible spatial relationships, we propose Shared Commonality Preference Optimization to enhance the model's understanding of spatial commonality across high-quality winning samples, further promoting shared spatial rationality.

📄 PDF Abstract BibTeX arXiv:2512.15644

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models

2026-07-23 · Mingyu Wang, Weilin Jin, Wenbo Li, Haoyang Huang 외 arxiv

Despite remarkable progress in visual understanding, Multimodal Large Language Models (MLLMs) remain prone to hallucinations when reasoning about spatial relationships, often producing judgments that contradict the true …

Spatial Reasoning

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement

2026-05-12 · Zhenxin Qin, Qiang Li, Qingzhuo Wang, Ruiyang Qin 외 arxiv

Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that contradicts the visual input. Existing res…

Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting

2025-02-12 · Jiarui Wu, Zhuo Liu, Hangfeng He

Spatial relation hallucinations pose a persistent challenge in large vision-language models (LVLMs), leading to generate incorrect predictions about object positions and spatial configurations within an image. To address…

Relation

Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning

2025-07-25 · Shengyuan Wang, Jie Feng, Tianhui Liu, Dan Pei 외 arxiv

Large language models (LLMs) possess extensive world knowledge, including geospatial knowledge, which has been successfully applied to various geospatial tasks such as mobility prediction and social indicator prediction.…

General KnowledgeKnowledge Graphs

Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models

2024-06-24 · Mingrui Wu, Jiayi Ji, Oucheng Huang, Jiale Li 외

The issue of hallucinations is a prevalent concern in existing Large Vision-Language Models (LVLMs). Previous efforts have primarily focused on investigating object hallucinations, which can be easily alleviated by intro…

Common Sense ReasoningHallucinationObject