Generation

EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos WACV 2025 EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene AAAI 2025 EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation CVPR 2025 Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis CVPR 2025 Elevating Flow-Guided Video Inpainting with Reference Generation AAAI 2025 Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models ICLR 2025 ELMGS: Enhancing Memory and Computation Scalability through Compression for 3D Gaussian Splatting WACV 2025 Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models WACV 2025 Elucidating the Solution Space of Extended Reverse-Time SDE for Diffusion Models WACV 2025 EMControl: Adding Conditional Control to Text-to-Image Diffusion Models via Expectation-Maximization AAAI 2025 EmoEdit: Evoking Emotions through Image Manipulation CVPR 2025 EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model ICCV 2025 EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion CVPR 2025 EmoVOCA: Speech-Driven Emotional 3D Talking Heads WACV 2025 Empowering LLMs to Understand and Generate Complex Vector Graphics CVPR 2025 Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility CVPR 2025 Empowering World Models with Reflection for Embodied Video Prediction ICML 2025 Enabling Region-Specific Control via Lassos in Point-Based Colorization AAAI 2025 Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis CVPR 2025 E-NeMF: Event-based Neural Motion Field for Novel Space-time View Synthesis of Dynamic Scenes ICCV 2025 Energy-Based Flow Matching for Generating 3D Molecular Structure ICML 2025 Energy-Guided Optimization for Personalized Image Editing with Pretrained Text-to-Image Diffusion Models AAAI 2025 EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space CVPR 2025 Engage for All: Making Ordinary Image Descriptions Appealing Again! ICCV 2025 Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation ACL 2025