Image Generation

DiHuR: Diffusion-Guided Generalizable Human Reconstruction WACV 2025 DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models ICCV 2025 Di[M]O: Distilling Masked Diffusion Models into One-step Generator ICCV 2025 Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator ICML 2025 DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation CVPR 2025 Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion Models AAAI 2025 Discovering Divergent Representations between Text-to-Image Models ICCV 2025 Disentangled Clothed Avatar Generation with Layered Representation ICCV 2025 Disentangled Pose and Appearance Guidance for Multi-Pose Generation CVPR 2025 DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation ICLR 2025 DisFlowEm : One-Shot Emotional Talking Head Generation using Disentangled Pose and Expression Flow-Guidance WACV 2025 Distillation of Discrete Diffusion through Dimensional Correlations ICML 2025 Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models ICCV 2025 Distributional Diffusion Models with Scoring Rules ICML 2025 DiT4Edit: Diffusion Transformer for Image Editing AAAI 2025 DivAvatar: Diverse 3D Avatar Generation with a Single Prompt WACV 2025 DIVE: Taming DINO for Subject-Driven Video Editing ICCV 2025 DLF: Extreme Image Compression with Dual-generative Latent Fusion ICCV 2025 DNF: Unconditional 4D Generation with Dictionary-based Neural Fields CVPR 2025 DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing WACV 2025 Document-level Simplification and Illustration Generation Multimodal Coherence EMNLP 2025 Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion ICML 2025 DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting CVPR 2025 Domain Generalizable Portrait Style Transfer ICCV 2025 Do Not DeepFake Me: Privacy-Preserving Neural 3D Head Reconstruction Without Sensitive Images AAAI 2025