9 papers
RAGMesh with FaME-G2E: Long-Form Text-Driven 3D Face Generation and Editing
Hao Li, Ju Dai, Feng Zhou +6
Text-driven 3D face generation and editing remains challenging due to the difficulty of translating long-form descriptions into fine-grained facial geometry. Existing methods prima…
COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping
Rui Yang, Wei Zhou, Dingyong Gou +5
Explainable aesthetic image cropping requires not only localizing a visually pleasing crop but also explaining why it is preferred. Existing crop-and-explain methods largely treat…
Modeling Scientific Experiment Scenes: Dataset and Model
Minghao Zou, Qingtian Zeng, Shangkun Liu +5
Scene Graph Generation (SGG) is fundamental to structured visual understanding, yet existing benchmarks focus mainly on daily-life images and overlook scientific experiment scenes…
The 1st PortraitCraft Challenge: A CVPR 2026 Workshop Competition on Portrait Composition Understanding and Generation
Zijie Lou, Youyun Tang, Xiaochao Qu +40
This paper presents an overview of the inaugural PortraitCraft Challenge, held as one of the official competitions at CVPR 2026. The challenge focuses on portrait composition under…
PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experiments
Minghao Zou, Qingtian Zeng, Shangkun Liu +5
Scene Graphs (SGs) provide structured representations of visual scenes by modeling objects and their pairwise relationships. Despite recent progress, existing datasets primarily fo…
FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning
Haihao Lin, Xiangsheng Huang, Xiao Yang +7
Action-supervised fine-tuning of vision-language-action (VLA) policies fits demonstrations effectively but constrains only the directions that change predicted actions, leaving vis…