AAAI-2024 扩散模型(Diffusion Model)相关论文（65篇）
Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/008af89b52
文章链接:(10.1609/aaai.v38i4.28147)
Audio Generation with Multiple Conditional Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/027b58e670
文章链接:(10.1609/aaai.v38i16.29773)
All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/0cd849213a
文章链接:(10.1609/aaai.v38i19.30107)
A Diffusion Model with State Estimation for Degradation-Blind Inverse Imaging
文章解读: http://www.studyai.com/xueshu/paper/detail/0fe184c794
文章链接:(10.1609/aaai.v38i3.28023)
SkipDiff: Adaptive Skip Diffusion Model for High-Fidelity Perceptual Image Super-resolution
文章解读: http://www.studyai.com/xueshu/paper/detail/10df872d83
文章链接:(10.1609/aaai.v38i5.28195)
DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/1108f7ee81
文章链接:(10.1609/aaai.v38i2.27824)
G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/145772416d
文章链接:(10.1609/aaai.v38i6.28441)
Understanding the Generalization of Pretrained Diffusion Models on Out-of-Distribution Data
文章解读: http://www.studyai.com/xueshu/paper/detail/189800e01e
文章链接:(10.1609/aaai.v38i13.29395)
Compositional Inversion for Stable Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/285aa09e22
文章链接:(10.1609/aaai.v38i7.28565)
ResDiff: Combining CNN and Diffusion Model for Image Super-resolution
文章解读: http://www.studyai.com/xueshu/paper/detail/297781ba83
文章链接:(10.1609/aaai.v38i8.28746)
Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/2b215ff703
文章链接:(10.1609/aaai.v38i7.28550)
AltDiffusion: A Multilingual Text-to-Image Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/2b806d3312
文章链接:(10.1609/aaai.v38i7.28487)
Rethinking Peculiar Images by Diffusion Models: Revealing Local Minima’s Role
文章解读: http://www.studyai.com/xueshu/paper/detail/2ecfa03623
文章链接:(10.1609/aaai.v38i3.28021)
Frequency-Controlled Diffusion Model for Versatile Text-Guided Image-to-Image Translation
文章解读: http://www.studyai.com/xueshu/paper/detail/312d985b9c
文章链接:(10.1609/aaai.v38i3.27951)
DiffRAW: Leveraging Diffusion Model to Generate DSLR-Comparable Perceptual Quality sRGB from Smartphone RAW Images
文章解读: http://www.studyai.com/xueshu/paper/detail/349bcc8000
文章链接:(10.1609/aaai.v38i7.28494)
Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/3e7fa4df20
文章链接:(10.1609/aaai.v38i7.28602)
Step Vulnerability Guided Mean Fluctuation Adversarial Attack against Conditional Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/418d232777
文章链接:(10.1609/aaai.v38i7.28503)
Text Image Inpainting via Global Structure-Guided Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/420940960f
文章链接:(10.1609/aaai.v38i7.28612)
Vector Field Oriented Diffusion Model for Crystal Material Generation
文章解读: http://www.studyai.com/xueshu/paper/detail/49216b2f73
文章链接:(10.1609/aaai.v38i20.30224)
Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification
文章解读: http://www.studyai.com/xueshu/paper/detail/49e13d100c
文章链接:(10.1609/aaai.v38i4.28084)
On Inference Stability for Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/4c6a82b960
文章链接:(10.1609/aaai.v38i13.29359)
Multi-Architecture Multi-Expert Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/5683794a79
文章链接:(10.1609/aaai.v38i12.29245)
Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/640ad84621
文章链接:(10.1609/aaai.v38i6.28364)
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
文章解读: http://www.studyai.com/xueshu/paper/detail/66affef9e9
文章链接:(10.1609/aaai.v38i10.28958)
KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding
文章解读: http://www.studyai.com/xueshu/paper/detail/67d6948ffe
文章链接:(10.1609/aaai.v38i8.28732)
DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/69be06c72e
文章链接:(10.1609/aaai.v38i19.30186)
Collaborative Tooth Motion Diffusion Model in Digital Orthodontics
文章解读: http://www.studyai.com/xueshu/paper/detail/6a2cc4c785
文章链接:(10.1609/aaai.v38i2.27935)
Controllable Mind Visual Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/6bb19f6a03
文章链接:(10.1609/aaai.v38i7.28519)
Stitching Sub-trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL
文章解读: http://www.studyai.com/xueshu/paper/detail/6c4335afcb
文章链接:(10.1609/aaai.v38i12.29215)
Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network
文章解读: http://www.studyai.com/xueshu/paper/detail/7071b40f37
文章链接:(10.1609/aaai.v38i6.28392)
Procedural Level Generation with Diffusion Models from a Single Example
文章解读: http://www.studyai.com/xueshu/paper/detail/70f9fb8251
文章链接:(10.1609/aaai.v38i9.28865)
T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/79ad32178d
文章链接:(10.1609/aaai.v38i5.28226)
Region-Disentangled Diffusion Model for High-Fidelity PPG-to-ECG Translation
文章解读: http://www.studyai.com/xueshu/paper/detail/7a0b622e79
文章链接:(10.1609/aaai.v38i13.29422)
O^2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/7a4363b576
文章链接:(10.1609/aaai.v38i3.28002)
AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/7a760bd8de
文章链接:(10.1609/aaai.v38i8.28696)
A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation
文章解读: http://www.studyai.com/xueshu/paper/detail/811ea64e37
文章链接:(10.1609/aaai.v38i1.27749)
TexFit: Text-Driven Fashion Image Editing with Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/8557c375fc
文章链接:(10.1609/aaai.v38i9.28885)
HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback
文章解读: http://www.studyai.com/xueshu/paper/detail/88fd0c0862
文章链接:(10.1609/aaai.v38i3.27974)
Music Style Transfer with Time-Varying Inversion of Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/935cc6fbce
文章链接:(10.1609/aaai.v38i1.27810)
Plug-In Diffusion Model for Sequential Recommendation
文章解读: http://www.studyai.com/xueshu/paper/detail/9bd69e2a2e
文章链接:(10.1609/aaai.v38i8.28736)
MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance
文章解读: http://www.studyai.com/xueshu/paper/detail/a675ae91d9
文章链接:(10.1609/aaai.v38i2.27899)
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/a708185bf0
文章链接:(10.1609/aaai.v38i19.30110)
DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion
文章解读: http://www.studyai.com/xueshu/paper/detail/a792f956b7
文章链接:(10.1609/aaai.v38i16.29740)
Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/a85218686f
文章链接:(10.1609/aaai.v38i17.29840)
DiffBEV: Conditional Diffusion Model for Bird’s Eye View Perception
文章解读: http://www.studyai.com/xueshu/paper/detail/a899b2ab3e
文章链接:(10.1609/aaai.v38i7.28620)
Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement
文章解读: http://www.studyai.com/xueshu/paper/detail/aa2288b12e
文章链接:(10.1609/aaai.v38i5.28273)
Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/abfd5b4273
文章链接:(10.1609/aaai.v38i2.27855)
ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/ac685d10c3
文章链接:(10.1609/aaai.v38i13.29371)
Exploring One-Shot Semi-supervised Federated Learning with Pre-trained Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/b0e68caf2f
文章链接:(10.1609/aaai.v38i15.29568)
SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/b1b75aff3e
文章链接:(10.1609/aaai.v38i6.28429)
Fair Sampling in Diffusion Models through Switching Mechanism
文章解读: http://www.studyai.com/xueshu/paper/detail/b384f887ed
文章链接:(10.1609/aaai.v38i20.30202)
Generating Images of Rare Concepts Using Pre-trained Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/c1e9ffda82
文章链接:(10.1609/aaai.v38i5.28270)
DiffusionTrack: Diffusion Model for Multi-Object Tracking
文章解读: http://www.studyai.com/xueshu/paper/detail/c3e0073a5b
文章链接:(10.1609/aaai.v38i5.28192)
Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
文章解读: http://www.studyai.com/xueshu/paper/detail/c745761c8e
文章链接:(10.1609/aaai.v38i1.27787)
SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-Form Layout-to-Image Generation
文章解读: http://www.studyai.com/xueshu/paper/detail/c99926d3de
文章链接:(10.1609/aaai.v38i3.28024)
ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank
文章解读: http://www.studyai.com/xueshu/paper/detail/d25a6a266b
文章链接:(10.1609/aaai.v38i7.28570)
Binding-Adaptive Diffusion Models for Structure-Based Drug Design
文章解读: http://www.studyai.com/xueshu/paper/detail/d379ca8a0f
文章链接:(10.1609/aaai.v38i11.29162)
Hyperbolic Graph Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/d515189fa2
文章链接:(10.1609/aaai.v38i14.29512)
Trade-Offs in Fine-Tuned Diffusion Models between Accuracy and Interpretability
文章解读: http://www.studyai.com/xueshu/paper/detail/ed6b28e3a6
文章链接:(10.1609/aaai.v38i19.30095)
Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution
文章解读: http://www.studyai.com/xueshu/paper/detail/eeb7aef00b
文章链接:(10.1609/aaai.v38i7.28511)
CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/eeeae16d16
文章链接:(10.1609/aaai.v38i2.27890)
LDMVFI: Video Frame Interpolation with Latent Diffusion Models
文章解读: http://www.studyai.com/xueshu/paper/detail/f4bfa05666
文章链接:(10.1609/aaai.v38i2.27912)
Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model
文章解读: http://www.studyai.com/xueshu/paper/detail/f530c4090e
文章链接:(10.1609/aaai.v38i6.28443)
Social Physics Informed Diffusion Model for Crowd Simulation
文章解读: http://www.studyai.com/xueshu/paper/detail/fb2586863b
文章链接:(10.1609/aaai.v38i1.27802)
扫一扫
397
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
