denoising
The task of removing noise or irrelevant information from data, particularly in image and audio processing, often enhancing the clarity and quality of the input before further analysis.
- DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
- EVODiff: Entropy-aware Variance Optimized Diffusion Inference
- Emergent Temporal Correspondences from Video Diffusion Transformers
- Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging
- From Softmax to Score: Transformers Can Effectively Implement In-Context Denoising Steps
- Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals
- Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks
- Leveraging Conditional Dependence for Efficient World Model Denoising
- Locality in Image Diffusion Models Emerges from Data Statistics
- MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation
- REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
- RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation
- Self Iterative Label Refinement via Robust Unlabeled Learning
- Self-diffusion for Solving Inverse Problems
- ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On
- TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming
- The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model
- U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching
- UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes