ACMMM-2024 扩散模型(Diffusion Model)相关论文（43篇）

ACMMM-2024 扩散模型(Diffusion Model)相关论文（43篇）

StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/00f3f99f27

文章链接: (https://openreview.net/forum?id=jnQFcUU9Bw)

Non-uniform Timestep Sampling: Towards Faster Diffusion Model Training

文章解读: http://www.studyai.com/xueshu/paper/detail/0866ce41ef

文章链接: (https://openreview.net/forum?id=NQPJYEyiiM)

Geometry-Guided Diffusion Model with Masked Transformer for Robust Multi-View 3D Human Pose Estimation

文章解读: http://www.studyai.com/xueshu/paper/detail/0be538bdf1

文章链接: (https://openreview.net/forum?id=z9nEV02Ujx)

Product2IMG: Prompt-Free E-commerce Product Background Generation with Diffusion Model and Self-Improved LMM

文章解读: http://www.studyai.com/xueshu/paper/detail/0c0a5d4075

文章链接: (https://openreview.net/forum?id=Af8QoxY78G)

EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second

文章解读: http://www.studyai.com/xueshu/paper/detail/0e03ff0ff2

文章链接: (https://openreview.net/forum?id=ibEaSS6bQn)

ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/11405ff091

文章链接: (https://openreview.net/forum?id=WOp8uEVcFt)

FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/13d06b5931

文章链接: (https://openreview.net/forum?id=de7GoqU3Uv)

PathUp: Patch-wise Timestep Tracking for Multi-class Large Pathology Image Synthesising Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/1a85e91c0b

文章链接: (https://openreview.net/forum?id=A7VkIoEELI)

Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/1c6ed7975c

文章链接: (https://openreview.net/forum?id=bb0M2WYeng)

TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning

文章解读: http://www.studyai.com/xueshu/paper/detail/298d656f60

文章链接: (https://openreview.net/forum?id=ZXTY6h5f8d)

Cons2Plan: Vector Floorplan Generation from Various Conditions via a Learning Framework based on Conditional Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/3677e913c8

文章链接: (https://openreview.net/forum?id=xnpEpIqjUU)

LDStega: Practical and Robust Generative Image Steganography based on Latent Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/3ec736af5a

文章链接: (https://openreview.net/forum?id=kEqGgMgIlu)

QNCD: Quantization Noise Correction for Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/410e6750aa

文章链接: (https://openreview.net/forum?id=0aijVq844S)

Investigating Conceptual Blending of a Diffusion Model for Improving Nonword-to-Image Generation

文章解读: http://www.studyai.com/xueshu/paper/detail/426256a628

文章链接: (https://openreview.net/forum?id=EZHxCOnV7n)

Mitigating Social Biases in Text-to-Image Diffusion Models via Linguistic-Aligned Attention Guidance

文章解读: http://www.studyai.com/xueshu/paper/detail/45993730c4

文章链接: (https://openreview.net/forum?id=rtjZHEOcHx)

Speech Reconstruction from Silent Lip and Tongue Articulation by Diffusion Models and Text-Guided Pseudo Target Generation

文章解读: http://www.studyai.com/xueshu/paper/detail/534f552cff

文章链接: (https://openreview.net/forum?id=M87zOOryOG)

MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/6204af24ed

文章链接: (https://openreview.net/forum?id=rLw5583hMb)

QVD: Post-training Quantization for Video Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/652776b476

文章链接: (https://openreview.net/forum?id=Fz6FxJ4gJr)

IconDM: Text-Guided Icon Set Expansion Using Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/6882abb14e

文章链接: (https://openreview.net/forum?id=SsVVrDheMH)

CustomNet: Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/6c62f193d4

文章链接: (https://openreview.net/forum?id=0j60hdbzln)

Multi-Modal Diffusion Model for Recommendation

文章解读: http://www.studyai.com/xueshu/paper/detail/6e262ae643

文章链接: (https://openreview.net/forum?id=5QE0Hf37Le)

FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/759b4833a7

文章链接: (https://openreview.net/forum?id=bw3xRlHRtC)

MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation

文章解读: http://www.studyai.com/xueshu/paper/detail/796e422bea

文章链接: (https://openreview.net/forum?id=6PSVsL2kYi)

Evolving Storytelling: Benchmarks and Methods for New Character Customization with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/800e8af903

文章链接: (https://openreview.net/forum?id=l64w1TI1T8)

Consistency Guided Diffusion Model with Neural Syntax for Perceptual Image Compression

文章解读: http://www.studyai.com/xueshu/paper/detail/852e64ef06

文章链接: (https://openreview.net/forum?id=nSUMQhITdd)

Motion-aware Latent Diffusion Models for Video Frame Interpolation

文章解读: http://www.studyai.com/xueshu/paper/detail/85b703c1e4

文章链接: (https://openreview.net/forum?id=u0geEr7X2O)

Attentive Linguistic Tracking in Diffusion Models for Training-free Text-guided Image Editing

文章解读: http://www.studyai.com/xueshu/paper/detail/8d40c07f77

文章链接: (https://openreview.net/forum?id=efTur2naAS)

Data Generation Scheme for Thermal Modality with Edge-Guided Adversarial Conditional Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/8e4ff4c2da

文章链接: (https://openreview.net/forum?id=GSmdnRqbpD)

Conditional Diffusion Model for Open-ended Video Question Answering

文章解读: http://www.studyai.com/xueshu/paper/detail/935c6609d9

文章链接: (https://openreview.net/forum?id=5WdYACFOhI)

FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/944126da61

文章链接: (https://openreview.net/forum?id=fodBlwAFMZ)

Digging into contrastive learning for robust depth estimation with diffusion models

文章解读: http://www.studyai.com/xueshu/paper/detail/95d2f43809

文章链接: (https://openreview.net/forum?id=eyYcMjUtJ4)

FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/98e632ae3d

文章链接: (https://openreview.net/forum?id=rdN6HJo3hD)

UniDense: Unleashing Diffusion Models with Meta-Routers for Universal Few-Shot Dense Prediction

文章解读: http://www.studyai.com/xueshu/paper/detail/9922339e61

文章链接: (https://openreview.net/forum?id=I8s3kmD82D)

Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/9fd4f2cb3b

文章链接: (https://openreview.net/forum?id=VEHNTupyIU)

CFDiffusion: Controllable Foreground Relighting in Image Compositing via Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/abcfbee699

文章链接: (https://openreview.net/forum?id=jFlt7lbZoB)

Unpaired Photo-realistic Image Deraining with Energy-informed Diffusion Model

文章解读: http://www.studyai.com/xueshu/paper/detail/aca6ebfd3a

文章链接: (https://openreview.net/forum?id=9ACKEhyS8u)

Towards Photorealistic Video Colorization via Gated Color-Guided Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/ae1e1c3317

文章链接: (https://openreview.net/forum?id=4k79es7Guv)

PROMOTE: Prior-Guided Diffusion Model with Global-Local Contrastive Learning for Exemplar-Based Image Translation

文章解读: http://www.studyai.com/xueshu/paper/detail/b28a618ef7

文章链接: (https://openreview.net/forum?id=w1fvy1Bhqj)

Interpretable Matching of Optical-SAR Image via Dynamically Conditioned Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/beadb90de4

文章链接: (https://openreview.net/forum?id=clKjOYw22x)

DreamVTON: Customizing 3D Virtual Try-on with Personalized Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/d536d35346

文章链接: (https://openreview.net/forum?id=AVWZuwrl8l)

JoReS-Diff: Joint Retinex and Semantic Priors in Diffusion Model for Low-light Image Enhancement

文章解读: http://www.studyai.com/xueshu/paper/detail/e95850d552

文章链接: (https://openreview.net/forum?id=kE1mWdsJRm)

Decoder-Only LLMs are Better Controllers for Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/eb9eb754e7

文章链接: (https://openreview.net/forum?id=0nEEsPOT0r)

Unveiling Structural Memorization: Structural Membership Inference Attack for Text-to-Image Diffusion Models

文章解读: http://www.studyai.com/xueshu/paper/detail/fc8b523251

文章链接: (https://openreview.net/forum?id=GQkPMFUWVf)