CVPR-2024-Papers Application Previous Collections Image and Video Synthesis and Generation Title Repo Paper Video Alchemist: Parametric Control of Material Properties with Diffusion Models ➖ Analyzing and Improving the Training Dynamics of Diffusion Models ➖ Attention Calibration for Disentangled Text-to-Image Personalization ➖ FreeU: Free Lunch in Diffusion U-Net Generative Image Dynamics ➖ Instruct-Imagen: Image Generation with Multi-Modal Instruction ➖ NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following Style Aligned Image Generation via Shared Attention ➖ Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models ➖ Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models ➖ Amodal Completion via Progressive Mixed Context Diffusion ➖ CLiC: Concept Learning in Context Clockwork Diffusion: Efficient Generation with Model-Step Distillation Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis CoDeF: Content Deformation Fields for Temporally Consistent Video Processing ➖ Correcting Diffusion Generation through Resampling ➖ CosmicMan: A Text-to-Image Foundation Model for Humans DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations ➖ Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models Don't Drop Your Samples! Coherence-Aware Training Benefits Conditional Diffusion DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing Dynamic Policy-Driven Adaptive Multi-Instance Learning for whole Slide Image Classification Fast ODE-based Sampling for Diffusion Models in Around 5 Steps ➖ FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis Generative Powers of Ten ➖ HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting Image Neural Field Diffusion Models ➖ Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation ➖ LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis ➖ One-Dimensional Adapter to Rule them All: Concepts Diffusion Models and Erasing Applications ➖ Orthogonal Adaptation for Modular Customization of Diffusion Models PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis Emu Edit: Precise Image Editing via Recognition and Generation Tasks Predicated Diffusion: Predicate Logic-based Attention Guidance for Text-to-Image Diffusion Models ➖ ➖ RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models Readout Guidance: Learning Control from Diffusion Features ➖ Real-Time 3D-Aware Portrait Video Relighting ➖ Residual Learning in Diffusion Models ➖ ➖ Rethinking FID: Towards a Better Evaluation Metric for Image Generation ➖ Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion ➖ SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models ➖ Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis Style Injection in Diffusion: A Training-Free Approach for Adapting Large-Scale Diffusion Models for Style Transfer ➖ Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models Taming Stable Diffusion for Text to 360 Panorama Image Generation ➖ TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models ➖ Total Selfie: Generating Full-Body Selfies UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs ➖ ➖ VecFusion: Vector Font Generation with Diffusion ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models ➖ 3D Geometry-Aware Deformable Gaussian Splatting for Dynamic View Synthesis 3D Multi-Frame Fusion for Video Stabilization ➖ 4D-fy: Text-to-4D Generation using Hybrid Score Distillation Sampling ➖ 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model ➖ RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization ➖ Ƶ*: Zero-Shot Style Transfer via Attention Reweighting ➖ A Recipe for Scaling up Text-to-Video Generation with Text-Free Videos A Unified Approach for Text- and Image-guided 4D Scene Generation ➖ A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing Accelerating Diffusion Sampling with Optimized Time Steps ➖ ACT-Diffusion: Efficient Adversarial Consistency Training for One-Step Diffusion Models ➖ Adversarial Score Distillation: When Score Distillation Meets GAN ➖ Adversarial Text to Continuous Image Generation ➖ AEROBLADE: Training-Free Detection of Latent Diffusion Images using Autoencoder Reconstruction Error Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation Animating General Image with Large Visual Motion Model ➖ Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability ➖ ➖ AnyDoor: Zero-Shot Object-Level Image Customization AnyScene: Customized Image Synthesis with Composited Foreground ➖ Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder ➖ ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation AVID: Any-Length Video Inpainting with Diffusion Model Balancing Act: Distribution-Guided Debiasing in Diffusion Models BerfScene: Bev-Conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation ➖ Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion ➖ ➖ Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models ➖ Boosting Diffusion Models with Moving Average Sampling in Frequency Domain ➖ C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video ➖ Cache Me if You Can: Accelerating Diffusion Models through Block Caching CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-Driven Video Editing CapHuman: Capture Your Moments in Parallel Universes ➖ Carve3D: Improving Multi-View Reconstruction Consistency for Diffusion Models with RL Finetuning ➖ CAT-DM: Controllable Accelerated Virtual Try-On with Diffusion Model CCEdit: Creative and Controllable Video Editing via Diffusion Models CDFormer: When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution ➖ CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization Check Locate Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation ➖ Cinematic Behavior Transfer via NeRF-based Differentiable Filming ➖ Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling ➖ CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation ➖ Combining Frame and GOP Embeddings for Neural Video Representation ➖ ➖ CommonCanvas: Open Diffusion Models Trained on Creative-Commons Images ➖ Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models ➖ Condition-Aware Neural Network for Controlled Image Generation CONFORM: Contrast is All You Need for High-Fidelity Text-to-Image Diffusion Models ➖ ConsistNet: Enforcing 3D Consistency for Multi-View Images Diffusion Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth Contrastive Denoising Score for Text-Guided Latent Diffusion Image Editing ControlRoom3D: Room Generation using Semantic Proxy Rooms Cross Initialization for Face Personalization of Text-to-Image Models ➖ Customization Assistant for Text-to-Image Generation ➖ ➖ Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement Deformable One-Shot Face Stylization via DINO Semantic Guidance DemoCaricature: Democratising Caricature Generation with a Rough Sketch DemoFusion: Democratising High-Resolution Image Generation with No $$$ DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception ➖ ➖ DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model ➖ DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing ➖ DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation ➖ ➖ DiffSHEG: A Diffusion-based Approach for Real-Time Speech-Driven Holistic 3D Expression and Gesture Generation Diffusion Model Alignment using Direct Preference Optimization ➖ Diffusion Models without Attention ➖ ➖ Direct2.5: Diverse Text-to-3D Generation via Multi-View 2.5D Diffusion ➖ DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data ➖ DisCo: Disentangled Control for Realistic Human Dance Generation Discriminative Probing and Tuning for Text-to-Image Generation ➖ Distilling ODE Solvers of Diffusion Models into Smaller Steps ➖ Diversity-Aware Channel Pruning for StyleGAN Compression Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting Doubly Abductive Counterfactual Inference for Text-based Image Editing Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation DREAM: Diffusion Rectification and Estimation-Adaptive Models ➖ DreamComposer: Controllable 3D Object Generation via Multi-View Conditions ➖ DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation ➖ ➖ DreamVideo: Composing Your Dream Videos with Customized Subject and Motion DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing Dysen-VDM: Empowering Dynamics-Aware Text-to-Video Diffusion with LLMs EasyDrag: Efficient Point-based Manipulation on Diffusion Models ➖ ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations ➖ Edit One for All: Interactive Batch Image Editing ➖ ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation ➖ EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models ➖ EMOPortraits: Emotion-enhanced Multimodal One-Shot Head Avatars ➖ Exact Fusion via Feature Distribution Matching for Few-Shot Image Generation Exploiting Diffusion Prior for Generalizable Dense Prediction Face2Diffusion for Fast and Editable Face Personalization FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-Shot Subject-Driven Generation ➖ Faces that Speak: Jointly Synthesising Talking Face and Speech from Text Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis ➖ Fixed Point Diffusion Models ➖ Focus on Your Instruction: Fine-grained and Multi-Instruction Image Editing by Attention Modulation FreeControl: Training-Free Spatial Control of any Text-to-Image Diffusion Model with any Condition ➖ FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition ➖ FreeDrag: Feature Dragging for Reliable Point-based Image Editing FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-Pose and Facial Expression Features Gaussian Shell Maps for Efficient 3D Human Generation GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models ➖ GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image