Image Generation

Zero-to-Hero enhances zero-shot novel view synthesis by cleverly filtering attention maps during inference, achieving significantly higher fidelity and realism without retraining.

MimicBrush: a novel image editing approach using reference imitation for intuitive zero-shot edits.

Warped Diffusion cleverly adapts image diffusion models for video inverse problems, solving flickering and temporal inconsistency issues by viewing video frames as continuous warping transformations a…

Vivid-ZOO: Generating high-quality multi-view videos from text using a novel diffusion model.

Researchers developed a novel zero-shot EEG-based framework for visual reconstruction using a tailored brain encoder and a two-stage image generation strategy, achieving state-of-the-art performance i…

Visual Autoregressive Modeling (VAR) revolutionizes image generation by using a coarse-to-fine ’next-scale prediction’, outperforming diffusion models and exhibiting scaling laws similar to LLMs.

Unsupervised learning framework enables high-fidelity non-line-of-sight (NLOS) imaging from irregularly undersampled transients, surpassing state-of-the-art methods in speed and robustness.

UPS: A novel algorithm for lightweight single-image super-resolution, decoupling feature extraction and similarity modeling for enhanced efficiency and robustness.

Untrained neural networks revolutionize snapshot compressive imaging (SCI) by enabling high-dimensional data recovery from a single 2D measurement, achieving state-of-the-art results without needing e…

AltO: a novel unsupervised learning framework for accurately estimating homography from multimodal image pairs, achieving performance comparable to supervised methods.

Self-guidance boosts masked generative models’ image synthesis, achieving superior quality and diversity with fewer steps!

ProjDiff: A novel algorithm unleashes diffusion models’ denoising power for superior inverse problem solutions.

UniFL: Unified Feedback Learning revolutionizes latent diffusion models by improving image quality, aesthetics, and inference speed through a unified feedback learning framework, surpassing existing m…

Enhance deep neural network privacy and trustworthiness with unified gradient-based machine unlearning, leveraging remain geometry for efficient forgetting and performance preservation.

Diffusion models generate unrealistic images by smoothly interpolating between data modes; this paper identifies this ‘mode interpolation’ failure and proposes a metric to detect and reduce it.

Training-free guidance revolutionizes diffusion models by enabling zero-shot conditional generation, but suffers from misaligned gradients and slow convergence. This paper provides theoretical analysi…

UltraPixel generates high-quality images at various resolutions (1K-6K) efficiently using cascade diffusion models, achieving state-of-the-art performance.

UDPM: Upsampling Diffusion Probabilistic Models achieves high-quality image generation with fewer computations by incorporating downsampling and upsampling within the diffusion process.

U-DiT: Revolutionizing diffusion transformers with a U-Net design and token downsampling for superior image generation and drastically reduced computation cost.

AdaptiveDiffusion accelerates diffusion model inference by adaptively skipping noise prediction steps, achieving 2-5x speedup without quality loss.