CVPR-2024 扩散模型(Diffusion Model)相关论文 PART1（83篇）

CVPR-2024 扩散模型(Diffusion Model)相关论文 PART1（83篇）

Alchemist: Parametric Control of Material Properties with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/00af847b59

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Sharma_Alchemist_Parametric_Control_of_Material_Properties_with_Diffusion_Models_CVPR_2024_paper.html)

CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion

文章解读: http://www.studyai.com/xueshu/paper/detail/02650e0007

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Wu_CGI-DM_Digital_Copyright_Authentication_for_Diffusion_Models_via_Contrasting_Gradient_CVPR_2024_paper.html)

DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data

文章解读: http://www.studyai.com/xueshu/paper/detail/02db6a9f39

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Ye_DiffusionMTL_Learning_Multi-Task_Denoising_Diffusion_Model_from_Partially_Annotated_Data_CVPR_2024_paper.html)

InstructVideo: Instructing Video Diffusion Models with Human Feedback

文章解读: http://www.studyai.com/xueshu/paper/detail/043708c70a

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Yuan_InstructVideo_Instructing_Video_Diffusion_Models_with_Human_Feedback_CVPR_2024_paper.html)

Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning

文章解读: http://www.studyai.com/xueshu/paper/detail/04834c9c62

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Miao_Training_Diffusion_Models_Towards_Diverse_Image_Generation_with_Reinforcement_Learning_CVPR_2024_paper.html)

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/0837af0cbe

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Shi_BIVDiff_A_Training-Free_Framework_for_General-Purpose_Video_Synthesis_via_Bridging_CVPR_2024_paper.html)

SVGDreamer: Text Guided SVG Generation with Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/08b09904ac

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Xing_SVGDreamer_Text_Guided_SVG_Generation_with_Diffusion_Model_CVPR_2024_paper.html)

Layout-Agnostic Scene Text Image Synthesis with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/0a49a8f854

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Zhangli_Layout-Agnostic_Scene_Text_Image_Synthesis_with_Diffusion_Models_CVPR_2024_paper.html)

Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/0d40aa4b71

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Dong_Building_Bridges_across_Spatial_and_Temporal_Resolutions_Reference-Based_Super-Resolution_via_CVPR_2024_paper.html)

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/0da6627c2b

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Huang_TFMQ-DM_Temporal_Feature_Maintenance_Quantization_for_Diffusion_Models_CVPR_2024_paper.html)

360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/0f48413a14

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Wang_360DVD_Controllable_Panorama_Video_Generation_with_360-Degree_Video_Diffusion_Model_CVPR_2024_paper.html)

Inversion-Free Image Editing with Language-Guided Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/0f5ea8782c

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Xu_Inversion-Free_Image_Editing_with_Language-Guided_Diffusion_Models_CVPR_2024_paper.html)

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner

文章解读: http://www.studyai.com/xueshu/paper/detail/100739f53d

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Xia_Towards_More_Accurate_Diffusion_Model_Acceleration_with_A_Timestep_Tuner_CVPR_2024_paper.html)

StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

文章解读: http://www.studyai.com/xueshu/paper/detail/102ef503be

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Kim_StableVITON_Learning_Semantic_Correspondence_with_Latent_Diffusion_Model_for_Virtual_CVPR_2024_paper.html)

Prompt-Free Diffusion: Taking “Text” out of Text-to-Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/131cf98157

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Xu_Prompt-Free_Diffusion_Taking_Text_out_of_Text-to-Image_Diffusion_Models_CVPR_2024_paper.html)

CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/13cfcf43c9

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Ranasinghe_CrowdDiff_Multi-hypothesis_Crowd_Density_Estimation_using_Diffusion_Models_CVPR_2024_paper.html)

Image Neural Field Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/13d6d11f82

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Chen_Image_Neural_Field_Diffusion_Models_CVPR_2024_paper.html)

DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/15b04c6214

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Pan_DiffSCI_Zero-Shot_Snapshot_Compressive_Imaging_via_Iterative_Spectral_Diffusion_Model_CVPR_2024_paper.html)

Bidirectional Autoregessive Diffusion Model for Dance Generation

文章解读: http://www.studyai.com/xueshu/paper/detail/171276f3e0

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Zhang_Bidirectional_Autoregessive_Diffusion_Model_for_Dance_Generation_CVPR_2024_paper.html)

Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text

文章解读: http://www.studyai.com/xueshu/paper/detail/183499c993

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Baltatzis_Neural_Sign_Actors_A_Diffusion_Model_for_3D_Sign_Language_CVPR_2024_paper.html)

DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/18ca8bde75

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Islam_DiffuseMix_Label-Preserving_Data_Augmentation_with_Diffusion_Models_CVPR_2024_paper.html)

SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/18ea2aefa5

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Wang_SimAC_A_Simple_Anti-Customization_Method_for_Protecting_Face_Privacy_against_CVPR_2024_paper.html)

Point Cloud Pre-training with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/1f5c5b6783

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Zheng_Point_Cloud_Pre-training_with_Diffusion_Models_CVPR_2024_paper.html)

Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution

文章解读: http://www.studyai.com/xueshu/paper/detail/1fd6ad35fb

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Li_Rethinking_Diffusion_Model_for_Multi-Contrast_MRI_Super-Resolution_CVPR_2024_paper.html)

Residual Denoising Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/22782f49db

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Liu_Residual_Denoising_Diffusion_Models_CVPR_2024_paper.html)

Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts

文章解读: http://www.studyai.com/xueshu/paper/detail/23f9828fd7

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Ni_Generate_Subgoal_Images_before_Act_Unlocking_the_Chain-of-Thought_Reasoning_in_CVPR_2024_paper.html)

Analyzing and Improving the Training Dynamics of Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/249d932afd

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Karras_Analyzing_and_Improving_the_Training_Dynamics_of_Diffusion_Models_CVPR_2024_paper.html)

ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/25ba2dc9bb

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Shih_ExtraNeRF_Visibility-Aware_View_Extrapolation_of_Neural_Radiance_Fields_with_Diffusion_CVPR_2024_paper.html)

Grid Diffusion Models for Text-to-Video Generation

文章解读: http://www.studyai.com/xueshu/paper/detail/2747e621ef

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Lee_Grid_Diffusion_Models_for_Text-to-Video_Generation_CVPR_2024_paper.html)

Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/2c27778851

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Liu_Intelligent_Grimm_-_Open-ended_Visual_Storytelling_via_Latent_Diffusion_Models_CVPR_2024_paper.html)

SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation

文章解读: http://www.studyai.com/xueshu/paper/detail/2cda20165c

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Toker_SatSynth_Augmenting_Image-Mask_Pairs_through_Diffusion_Models_for_Aerial_Semantic_CVPR_2024_paper.html)

Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation

文章解读: http://www.studyai.com/xueshu/paper/detail/2e354bbd7f

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Wang_Towards_Effective_Usage_of_Human-Centric_Priors_in_Diffusion_Models_for_CVPR_2024_paper.html)

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/31e235fb8c

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Chen_VideoCrafter2_Overcoming_Data_Limitations_for_High-Quality_Video_Diffusion_Models_CVPR_2024_paper.html)

VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/31f7537d47

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Jeong_VMC_Video_Motion_Customization_using_Temporal_Attention_Adaption_for_Text-to-Video_CVPR_2024_paper.html)

In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification

文章解读: http://www.studyai.com/xueshu/paper/detail/3477e7850f

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Park_In-distribution_Public_Data_Synthesis_with_Diffusion_Models_for_Differentially_Private_CVPR_2024_paper.html)

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

文章解读: http://www.studyai.com/xueshu/paper/detail/351b1db34f

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Shi_DragDiffusion_Harnessing_Diffusion_Models_for_Interactive_Point-based_Image_Editing_CVPR_2024_paper.html)

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model

文章解读: http://www.studyai.com/xueshu/paper/detail/3530649522

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Yang_Using_Human_Feedback_to_Fine-tune_Diffusion_Models_without_Any_Reward_CVPR_2024_paper.html)

Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers

文章解读: http://www.studyai.com/xueshu/paper/detail/3756073ce6

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Koley_Text-to-Image_Diffusion_Models_are_Great_Sketch-Photo_Matchmakers_CVPR_2024_paper.html)

ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation

文章解读: http://www.studyai.com/xueshu/paper/detail/37a60d6279

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Patni_ECoDepth_Effective_Conditioning_of_Diffusion_Models_for_Monocular_Depth_Estimation_CVPR_2024_paper.html)

NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/3a677b6007

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Dalva_NoiseCLR_A_Contrastive_Learning_Approach_for_Unsupervised_Discovery_of_Interpretable_CVPR_2024_paper.html)

DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

文章解读: http://www.studyai.com/xueshu/paper/detail/3a75633c7b

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Scarpellini_DiffAssemble_A_Unified_Graph-Diffusion_Model_for_2D_and_3D_Reassembly_CVPR_2024_paper.html)

Towards Accurate Post-training Quantization for Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/3b4e0966c5

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Wang_Towards_Accurate_Post-training_Quantization_for_Diffusion_Models_CVPR_2024_paper.html)

MatFuse: Controllable Material Generation with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/3bfa3d05ca

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Vecchio_MatFuse_Controllable_Material_Generation_with_Diffusion_Models_CVPR_2024_paper.html)

FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/3de3d78d46

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Luo_FlowDiffuser_Advancing_Optical_Flow_Estimation_with_Diffusion_Models_CVPR_2024_paper.html)

Hierarchical Patch Diffusion Models for High-Resolution Video Generation

文章解读: http://www.studyai.com/xueshu/paper/detail/3dfb22d3bb

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Skorokhodov_Hierarchical_Patch_Diffusion_Models_for_High-Resolution_Video_Generation_CVPR_2024_paper.html)

Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture

文章解读: http://www.studyai.com/xueshu/paper/detail/3ec588f171

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Zhang_Improving_Training_Efficiency_of_Diffusion_Models_via_Multi-Stage_Framework_and_CVPR_2024_paper.html)

SODA: Bottleneck Diffusion Models for Representation Learning

文章解读: http://www.studyai.com/xueshu/paper/detail/409349396f

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Hudson_SODA_Bottleneck_Diffusion_Models_for_Representation_Learning_CVPR_2024_paper.html)

Bayesian Diffusion Models for 3D Shape Reconstruction

文章解读: http://www.studyai.com/xueshu/paper/detail/414f9d9748

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Xu_Bayesian_Diffusion_Models_for_3D_Shape_Reconstruction_CVPR_2024_paper.html)

HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/427584301e

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Pang_HIR-Diff_Unsupervised_Hyperspectral_Image_Restoration_Via_Improved_Diffusion_Models_CVPR_2024_paper.html)

Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution

文章解读: http://www.studyai.com/xueshu/paper/detail/44cea49723

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Chen_Learning_Spatial_Adaptation_and_Temporal_Coherence_in_Diffusion_Models_for_CVPR_2024_paper.html)

Video Interpolation with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/46caecfeb9

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Jain_Video_Interpolation_with_Diffusion_Models_CVPR_2024_paper.html)

Shadow Generation for Composite Image Using Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/48e2ef6c59

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Liu_Shadow_Generation_for_Composite_Image_Using_Diffusion_Model_CVPR_2024_paper.html)

Fixed Point Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/4af8ef5dcd

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Bai_Fixed_Point_Diffusion_Models_CVPR_2024_paper.html)

HOIAnimator: Generating Text-prompt Human-object Animations using Novel Perceptive Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/4de6fa7d58

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Song_HOIAnimator_Generating_Text-prompt_Human-object_Animations_using_Novel_Perceptive_Diffusion_Models_CVPR_2024_paper.html)

InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/504fa6b48b

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Hoe_InteractDiffusion_Interaction_Control_in_Text-to-Image_Diffusion_Models_CVPR_2024_paper.html)

HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

文章解读: http://www.studyai.com/xueshu/paper/detail/50df5f5ae4

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Huang_HumanNorm_Learning_Normal_Diffusion_Model_for_High-quality_and_Realistic_3D_CVPR_2024_paper.html)

MACE: Mass Concept Erasure in Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/513f768c20

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Lu_MACE_Mass_Concept_Erasure_in_Diffusion_Models_CVPR_2024_paper.html)

Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D

文章解读: http://www.studyai.com/xueshu/paper/detail/5248986ca6

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Pandey_Diffusion_Handles_Enabling_3D_Edits_for_Diffusion_Models_by_Lifting_CVPR_2024_paper.html)

Boosting Diffusion Models with Moving Average Sampling in Frequency Domain

文章解读: http://www.studyai.com/xueshu/paper/detail/550145e87c

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Qian_Boosting_Diffusion_Models_with_Moving_Average_Sampling_in_Frequency_Domain_CVPR_2024_paper.html)

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/596fabf345

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Li_SNED_Superposition_Network_Architecture_Search_for_Efficient_Video_Diffusion_Model_CVPR_2024_paper.html)

NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging

文章解读: http://www.studyai.com/xueshu/paper/detail/5eec1f72ed

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Shirakawa_NoiseCollage_A_Layout-Aware_Text-to-Image_Diffusion_Model_Based_on_Noise_Cropping_CVPR_2024_paper.html)

MMA-Diffusion: MultiModal Attack on Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/6091ba9bb4

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Yang_MMA-Diffusion_MultiModal_Attack_on_Diffusion_Models_CVPR_2024_paper.html)

AAMDM: Accelerated Auto-regressive Motion Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/663ba68cd6

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Li_AAMDM_Accelerated_Auto-regressive_Motion_Diffusion_Model_CVPR_2024_paper.html)

CONFORM: Contrast is All You Need for High-Fidelity Text-to-Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/6694aee584

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Meral_CONFORM_Contrast_is_All_You_Need_for_High-Fidelity_Text-to-Image_Diffusion_CVPR_2024_paper.html)

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/699a3e4cf1

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Cao_DreamAvatar_Text-and-Shape_Guided_3D_Human_Avatar_Generation_via_Diffusion_Models_CVPR_2024_paper.html)

Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/6b48131d56

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Mahajan_Prompting_Hard_or_Hardly_Prompting_Prompt_Inversion_for_Text-to-Image_Diffusion_CVPR_2024_paper.html)

FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition

文章解读: http://www.studyai.com/xueshu/paper/detail/6bbafe932b

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Mo_FreeControl_Training-Free_Spatial_Control_of_Any_Text-to-Image_Diffusion_Model_with_CVPR_2024_paper.html)

MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/6d73be43cf

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Song_MimicDiffusion_Purifying_Adversarial_Perturbation_via_Mimicking_Clean_Diffusion_Model_CVPR_2024_paper.html)

Towards Memorization-Free Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/6e1c65c4a3

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Chen_Towards_Memorization-Free_Diffusion_Models_CVPR_2024_paper.html)

Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

文章解读: http://www.studyai.com/xueshu/paper/detail/6ebe358047

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Chung_Style_Injection_in_Diffusion_A_Training-free_Approach_for_Adapting_Large-scale_CVPR_2024_paper.html)

CCEdit: Creative and Controllable Video Editing via Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/727d701991

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Feng_CCEdit_Creative_and_Controllable_Video_Editing_via_Diffusion_Models_CVPR_2024_paper.html)

D^4: Dataset Distillation via Disentangled Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/7324e3c1ce

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Su_D4_Dataset_Distillation_via_Disentangled_Diffusion_Model_CVPR_2024_paper.html)

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

文章解读: http://www.studyai.com/xueshu/paper/detail/742e8bfc85

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Wimbauer_Cache_Me_if_You_Can_Accelerating_Diffusion_Models_through_Block_CVPR_2024_paper.html)

Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/74c35b5317

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Zeng_Paint3D_Paint_Anything_3D_with_Lighting-Less_Texture_Diffusion_Models_CVPR_2024_paper.html)

DiffLoc: Diffusion Model for Outdoor LiDAR Localization

文章解读: http://www.studyai.com/xueshu/paper/detail/74ea377038

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Li_DiffLoc_Diffusion_Model_for_Outdoor_LiDAR_Localization_CVPR_2024_paper.html)

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/7680411f5b

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Guo_Smooth_Diffusion_Crafting_Smooth_Latent_Spaces_in_Diffusion_Models_CVPR_2024_paper.html)

Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/7697ca3ab2

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Starodubcev_Your_Student_is_Better_Than_Expected_Adaptive_Teacher-Student_Collaboration_for_CVPR_2024_paper.html)

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/7826ac271a

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Li_DistriFusion_Distributed_Parallel_Inference_for_High-Resolution_Diffusion_Models_CVPR_2024_paper.html)

ExtDM: Distribution Extrapolation Diffusion Model for Video Prediction

文章解读: http://www.studyai.com/xueshu/paper/detail/78b1b6bbda

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Zhang_ExtDM_Distribution_Extrapolation_Diffusion_Model_for_Video_Prediction_CVPR_2024_paper.html)

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/7aeca5ccc0

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Kim_WOUAF_Weight_Modulation_for_User_Attribution_and_Fingerprinting_in_Text-to-Image_CVPR_2024_paper.html)

EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/7bf18a7915

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Yang_EmoGen_Emotional_Image_Content_Generation_with_Text-to-Image_Diffusion_Models_CVPR_2024_paper.html)

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D

文章解读: http://www.studyai.com/xueshu/paper/detail/808e23c692

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Qiu_RichDreamer_A_Generalizable_Normal-Depth_Diffusion_Model_for_Detail_Richness_in_CVPR_2024_paper.html)

HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/81e0b4cf31

文章链接: (https://openaccess.thecvf.com/content/CVPR2024/html/Li_HHMR_Holistic_Hand_Mesh_Recovery_by_Enhancing_the_Multimodal_Controllability_CVPR_2024_paper.html)