CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics

arXiv:2512.07155 · cs.CV · Submitted 2025-12-08 · Read on arXiv

cs.CV

Submitted: 2025-12-08

Updated: 2026-10-10

Comments: Revised and restructured manuscript. Please visit our project page at https://cmlab-korea.github.io/CHIMERA/

Project page: https://cmlab-korea.github.io/CHIMERA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 1× in this paper · explained in 3 episodes
• Over-smoothing — 1× in this paper · explained in 4 episodes

Sources

• Qwen2.5-VL Technical Report
• Diffusion Models already have a Semantic Latent Space
• Classifier-Free Diffusion Guidance
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
• Qwen3 Technical Report
• DINOv2: Learning Robust Visual Features without Supervision
• The 2017 DAVIS Challenge on Video Object Segmentation
• AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation
• Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation
• LTX-Video: Realtime Video Latent Diffusion
• OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models