← Models
Deep Learning › Models ›

Diffusion Models

4342 directly classified papers

Papers per year

Papers

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image ICCV 2025
Blind Video Super-Resolution based on Implicit Kernels ICCV 2025
TACO: Taming Diffusion for in-the-wild Video Amodal Completion ICCV 2025
AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction ICCV 2025
IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves ICCV 2025
AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction ICCV 2025
OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting ICCV 2025
MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer ICCV 2025
ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis ICCV 2025
CObL: Toward Zero-Shot Ordinal Layering without User Prompting ICCV 2025
FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention ICCV 2025
Diffusion-Based Imaginative Coordination for Bimanual Manipulation ICCV 2025
Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis ICCV 2025
Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization ICCV 2025
Adaptive Caching for Faster Video Generation with Diffusion Transformers ICCV 2025
Free2Guide: Training-Free Text-to-Video Alignment using Image LVLM ICCV 2025
Moderating the Generalization of Score-based Generative Model ICCV 2025
CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation ICCV 2025
ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction ICCV 2025
Debiasing Trace Guidance: Top-down Trace Distillation and Bottom-up Velocity Alignment for Unsupervised Anomaly Detection ICCV 2025
Accelerating Diffusion Transformer via Gradient-Optimized Cache ICCV 2025
Instruction-based Image Editing with Planning, Reasoning, and Generation ICCV 2025
KV-Edit: Training-Free Image Editing for Precise Background Preservation ICCV 2025
Improving Rectified Flow with Boundary Conditions ICCV 2025
AV-Flow: Transforming Text to Audio-Visual Human-like Interactions ICCV 2025