A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
Mixed citations
IEEE Trans
Mixed citation behavior. Most common role is background (33%).
6
Pith papers citing it
Background
33% of classified citations
citation-role summary
background 2
method 2
baseline 1
dataset 1
citation-polarity summary
years
2026 6representative citing papers
MetaSR adaptively orchestrates metadata in a DiT-based generative SR model to deliver up to 1 dB PSNR gains and 50% bitrate savings across diverse content and degradations.
Recoverability maps use synthetic sweeps of viewing angles and artifacts to quantify the recoverable fraction of parameter space for license plate restoration, with the best model succeeding on 93% and geometry setting the limit over architecture choice.
ZID-Net decouples diffusion-based priors into a training-only head to create an efficient feed-forward network for single-image dehazing, reporting 40.75 dB PSNR on RESIDE and 19 ms inference.
DeepSignature embeds digitally signed content-encoding watermarks via neural networks for robust image authentication, source attribution, and latent-space tamper localization.
ACPO uses anchor-based regularization with NR-IQA guidance to enable stable perceptual quality improvements in diffusion model fine-tuning.
citing papers explorer
-
TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
-
MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution
MetaSR adaptively orchestrates metadata in a DiT-based generative SR model to deliver up to 1 dB PSNR gains and 50% bitrate savings across diverse content and degradations.
-
Mapping License Plate Recoverability Under Extreme Viewing Angles for Oppor-tunistic Urban Sensing
Recoverability maps use synthetic sweeps of viewing angles and artifacts to quantify the recoverable fraction of parameter space for license plate restoration, with the best model succeeding on 93% and geometry setting the limit over architecture choice.
-
ZID-Net: Zero-Inference Diffusion Prior Decoupling Network for Single Image Dehazing
ZID-Net decouples diffusion-based priors into a training-only head to create an efficient feed-forward network for single-image dehazing, reporting 40.75 dB PSNR on RESIDE and 19 ms inference.
-
DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication
DeepSignature embeds digitally signed content-encoding watermarks via neural networks for robust image authentication, source attribution, and latent-space tamper localization.
-
ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance
ACPO uses anchor-based regularization with NR-IQA guidance to enable stable perceptual quality improvements in diffusion model fine-tuning.