RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation
원문 초록
Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject image. Despite its broad downstream applicability -- ranging from enhanced personalization in image generation to consistent character representation in video rendering -- progress in this field is limited by the lack of reliable automatic evaluation. Existing methods either assess only one aspect of the task (i.e., textual alignment or subject preservation), misalign with human judgments, or rely on costly API-based evaluation. To address this, we introduce RefVNLI, a cost-effective metric that evaluates both textual alignment and subject preservation in a single prediction. Trained on a large-scale dataset derived from video-reasoning benchmarks and image perturbations, RefVNLI outperforms or matches existing baselines across multiple benchmarks and subject categories (e.g., \emph{Animal}, \emph{Object}), achieving up to 6.4-point gains in textual alignment and 8.5-point gains in subject consistency. It also excels with lesser-known concepts, aligning with human preferences at over 87\% accuracy.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CharaConsist: Fine-Grained Consistent Character Generation
NeoBabel: A Multilingual Open Tower for Visual Generation
Ovis-U1 Technical Report
Rethink Sparse Signals for Pose-guided Text-to-image Generation
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.