6 papers
VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing
Ziyun Zeng, Zixuan Wang, Yongsheng Yu +2
Evaluating generated videos remains challenging because existing benchmarks rely on fixed evaluation content, cover only a subset of generation and editing settings, and provide li…
Aurora: Unified Video Editing with a Tool-Using Agent
Yongsheng Yu, Ziyun Zeng, Zhiyuan Xiao +4
Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference images, and one set o…
PixelDiT: Pixel Diffusion Transformers for Image Generation
Yongsheng Yu, Wei Xiong, Weili Nie +3
Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstr…
PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement
Haitian Zheng, Yuan Yao, Yongsheng Yu +3
Latent Diffusion Models (LDMs) have markedly advanced the quality of image inpainting and local editing. However, the inherent latent compression often introduces pixel-level incon…
ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration
Yongsheng Yu, Haitian Zheng, Zhifei Zhang +7
Recent progress in generative models has significantly improved image restoration capabilities, particularly through powerful diffusion models that offer remarkable recovery of sem…
OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
Yongsheng Yu, Ziyun Zeng, Haitian Zheng +1
Diffusion-based generative models have revolutionized object-oriented image editing, yet their deployment in realistic object removal and insertion remains hampered by challenges s…