ROICtrl: Boosting Instance Control for Visual Generation
Natural language often struggles to accurately associate positional and attribute information with multiple instances, which limits current text-based visual generation models to simpler compositions featuring only a few dominant instances. To address this limitation, this work enhances diffusion models by introducing regional instance control, where each instance is governed by a bounding box paired with a free-form caption. Previous methods in this area typically rely on implicit position encoding or explicit attention masks to separate regions of interest (ROIs), resulting in either inaccurate coordinate injection or large computational overhead. Inspired by ROI-Align in object detection, we introduce a complementary operation called ROI-Unpool. Together, ROI-Align and ROI-Unpool enable explicit, efficient, and accurate ROI manipulation on high-resolution feature maps for visual generation. Building on ROI-Unpool, we propose ROICtrl, an adapter for pretrained diffusion models that enables precise regional instance control. ROICtrl is compatible with community-finetuned diffusion models, as well as with existing spatial-based add-ons (\eg, ControlNet, T2I-Adapter) and embedding-based add-ons (\eg, IP-Adapter, ED-LoRA), extending their applications to multi-instance generation. Experiments show that ROICtrl achieves superior performance in regional instance control while significantly reducing computational costs.
Code (0)
등록된 구현이 없습니다.
Tasks
Attributeobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
InstanceControl: Controllable Complex Image Generation without Instance Labeling
Controllable image generation methods, such as ControlNet, have demonstrated a remarkable capacity to introduce visual conditions(e.g., depth maps) to guide image generation. However, these methods often struggle with co…
Image GenerationInstance Significance Guided Multiple Instance Boosting for Robust Visual Tracking
Multiple Instance Learning (MIL) recently provides an appealing way to alleviate the drifting problem in visual tracking. Following the tracking-by-detection framework, an online MILBoost approach is developed that seque…
Multiple Instance LearningVisual TrackingLearning What To Hear: Boosting Sound-Source Association For Robust Audiovisual Instance Segmentation
Audiovisual instance segmentation (AVIS) requires accurately localizing and tracking sounding objects throughout video sequences. Existing methods suffer from visual bias stemming from two fundamental issues: uniform add…
Instance SegmentationConsistCompose: Unified Multimodal Layout Control for Image Composition
Unified multimodal models that couple visual understanding with image generation have advanced rapidly, yet most systems still focus on visual grounding-aligning language with image regions-while their generative counter…
Visual GroundingImage GenerationBoosting Dermatoscopic Lesion Segmentation via Diffusion Models with Visual and Textual Prompts
Image synthesis approaches, e.g., generative adversarial networks, have been popular as a form of data augmentation in medical image analysis tasks. It is primarily beneficial to overcome the shortage of publicly accessi…
Data AugmentationImage GenerationLesion SegmentationMedical Image Analysis+1