5 papers
Beyond Legibility: Benchmarking Visual Text Rendering and In-Place Editing in Unified Video Generation
Ziying Zhang, Litao Li, Junchao Liao +4
A video can exhibit convincing motion and photorealism yet fail immediately when visual text collapses. Unlike generic scene content, visual text is unforgiving in video generation…
Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation
Tianyi Zeng, Junchao Liao, Yujie Wei +9
Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute editing techniques. Profession…
Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence
Junchao Liao, Zhenghao Zhang, Xiangyu Meng +5
Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible motion-sound relations remains c…
LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing
Zhenghao Zhang, Ziying Zhang, Junchao Liao +6
Recent multimodal models for instruction-based face editing enable semantic manipulation but still struggle with precise attribute control and identity preservation. Structural fac…
TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration
Ziying Zhang, Xiang Gao, Zhixin Wang +2
Diffusion-based methodologies have shown significant potential in blind face restoration (BFR), leveraging their robust generative capabilities. However, they are often criticized…