Cover Image

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ouyang, Ziheng, Song, Yiren, Liu, Yaoli, Zhu, Shihao, Hou, Qibin, Cheng, Ming-Ming, Shou, Mike Zheng
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OmniRefiner: Reinforcement-Guided Local Diffusion Refinement
by: Liu, Yaoli, et al.
Published: (2025)

OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data
by: Song, Yiren, et al.
Published: (2025)

Mixture of Style Experts for Diverse Image Stylization
by: Zhu, Shihao, et al.
Published: (2026)

MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation
by: Song, Yiren, et al.
Published: (2025)

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
by: Zhou, Yupeng, et al.
Published: (2024)

Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers
by: Shi, Yiqing, et al.
Published: (2025)

IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
by: Song, Yiren, et al.
Published: (2024)

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
by: Song, Yiren, et al.
Published: (2025)

Mitty: Diffusion-based Human-to-Robot Video Generation
by: Song, Yiren, et al.
Published: (2025)

OmniPSD: Layered PSD Generation with Diffusion Transformer
by: Liu, Cheng, et al.
Published: (2025)

AgeBooth: Controllable Facial Aging and Rejuvenation via Diffusion Models
by: Zhu, Shihao, et al.
Published: (2025)

StreamingEffect: Real-Time Human-Centric Video Effect Generation
by: Song, Yiren, et al.
Published: (2026)

Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation
by: Song, Yiren, et al.
Published: (2024)

K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs
by: Ouyang, Ziheng, et al.
Published: (2025)

Sora Generates Videos with Stunning Geometrical Consistency
by: Li, Xuanyi, et al.
Published: (2024)

DiffSim: Taming Diffusion Models for Evaluating Visual Similarity
by: Song, Yiren, et al.
Published: (2024)

X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale
by: Yang, Pei, et al.
Published: (2025)

Referring Camouflaged Object Detection
by: Zhang, Xuying, et al.
Published: (2023)

AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction
by: Zhang, Xuying, et al.
Published: (2025)

WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation
by: Song, Quanjian, et al.
Published: (2025)

SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution
by: Song, Yiren, et al.
Published: (2026)

Personalized Vision via Visual In-Context Learning
by: Jiang, Yuxin, et al.
Published: (2025)

ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution
by: Wan, Yuhao, et al.
Published: (2024)

Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?
by: Yang, Pei, et al.
Published: (2024)

VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers
by: Song, Yiren, et al.
Published: (2026)

RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification
by: Ci, Hai, et al.
Published: (2024)

OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
by: Song, Yiren, et al.
Published: (2026)

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
by: Li, Yunheng, et al.
Published: (2024)

Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction
by: Li, Yunheng, et al.
Published: (2024)

Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment
by: Zhang, Shi-Chen, et al.
Published: (2025)

Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration
by: Song, Yiren, et al.
Published: (2026)

WMAdapter: Adding WaterMark Control to Latent Diffusion Models
by: Ci, Hai, et al.
Published: (2024)

UENR-600K: A Large-Scale Physically Grounded Dataset for Nighttime Video Deraining
by: Yang, Pei, et al.
Published: (2026)

H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos
by: Ci, Hai, et al.
Published: (2025)

Automated Movie Generation via Multi-Agent CoT Planning
by: Wu, Weijia, et al.
Published: (2025)

Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model
by: Mao, Qi, et al.
Published: (2025)

Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
by: Liu, Yepeng, et al.
Published: (2024)

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data
by: Huang, Shijie, et al.
Published: (2025)

Zone Evaluation: Revealing Spatial Bias in Object Detection
by: Zheng, Zhaohui, et al.
Published: (2023)

CrossKD: Cross-Head Knowledge Distillation for Object Detection
by: Wang, Jiabao, et al.
Published: (2023)