Diffusion Models

Generating Past and Future in Digital Painting Processes

Lvmin Zhang, Chuan Yan, Yuwei Guo, Jinbo Xing, Maneesh Agrawala

Journal SIGGRAPH 2025 Diffusion Models Video Diffusion Digital Painting Drawing Process Generation Generative Models Interactive Creation

ASIA: Adaptive 3D Segmentation using Few Image Annotations

Sai Raj Kishore Perla, Aditya Vora, Sauradip Nag, Ali Mahdavi-Amiri, Hao Zhang

Conference SIGGRAPH Asia 2025 3D Segmentation Diffusion Models Few-Shot Learning Part Segmentation Multi-View Consistency

Audio Driven Real-Time Facial Animation for Social Telepresence

Jiye Lee, Chenghui Li, Linh Tran, Shih-En Wei, Jason Saragih, Alexander Richard, Hanbyul Joo, Shaojie Bai

Conference SIGGRAPH Asia 2025 Audio-Driven Animation Facial Animation Diffusion Models Real-Time VR Telepresence

AutoSketch: VLM-assisted Style-Aware Vector Sketch Completion

Hsiao-Yuan Chin, I-Chao Shen, Yi-Ting Chiu, Ariel Shamir, Bing-Yu Chen

Conference SIGGRAPH Asia 2025 Vector Sketch Sketch Completion VLM Style-Aware Generation Diffusion Models

ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation

Yohai Mazuz, Janna Bruner, Lior Wolf

Journal SIGGRAPH Asia 2025 Text To Image Generation Consistent Character Generation Training Free Style Transfer Self Attention Diffusion Models AdaIN SDXL

MALeR: Improving Compositional Fidelity in Layout-Guided Generation

Shivank Saxena, Dhruv Srivastava, Makarand Tapaswi

Journal SIGGRAPH Asia 2025 Layout-Guided Generation Text-To-Image Diffusion Models Compositional Generation Attribute Binding Latent Optimization Training-Free

One-shot Embroidery Customization via Contrastive LoRA Modulation

Jun Ma, Qian He, Gaofeng He, Huang Chen, Chen Liu, Xiaogang Jin, Huamin Wang

Journal SIGGRAPH Asia 2025 Embroidery Customization Style Transfer Contrastive Learning LoRA Diffusion Models One-shot Learning Style Content Disentanglement

PractiLight: Practical Light Control Using Foundational Diffusion Models

Yotam Erel, Rishabh Dabral, Vladislav Golyanik, Amit H. Bermano, Christian Theobalt

Journal SIGGRAPH Asia 2025 Relighting Diffusion Models Light Transport Classifier Guidance LoRA Self Attention Image Editing