conftrace_
← Models
Deep Learning › Models ›

Diffusion Models

4,342 papers

Papers per year

Papers

Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition ICCV 2025
SceneMI: Motion In-betweening for Modeling Human-Scene Interaction ICCV 2025
Unlocking the Potential of Diffusion Priors in Blind Face Restoration ICCV 2025
Improved Noise Schedule for Diffusion Training ICCV 2025
ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition ICCV 2025
CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts ICCV 2025
Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts ICCV 2025
SpinMeRound: Consistent Multi-View Identity Generation Using Diffusion Models ICCV 2025
Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics ICCV 2025
Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis ICCV 2025
DiffPCI: Large Motion Point Cloud frame Interpolation with Diffusion Model ICCV 2025
TryOn-Refiner: Conditional Rectified-flow-based TryOn Refiner for More Accurate Detail Reconstruction ICCV 2025
MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics ICCV 2025
Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting ICCV 2025
Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization ICCV 2025
LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering ICCV 2025
LATINO-PRO: LAtent consisTency INverse sOlver with PRompt Optimization ICCV 2025
Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal ICCV 2025
AnyPortal: Zero-Shot Consistent Video Background Replacement ICCV 2025
Scene Coordinate Reconstruction Priors ICCV 2025
Balanced Image Stylization with Style Matching Score ICCV 2025
Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin ICCV 2025
SD2Actor: Continuous State Decomposition via Diffusion Embeddings for Robotic Manipulation ICCV 2025
Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation ICCV 2025
Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integrity ICCV 2025