3 accepted papers
Video Diffusion Transformers (DiTs) have been synthesizing high-quality video with high fidelity from given text descriptions involving motion. However, understanding how Video DiTs convert motion words into video remains insufficient. Furthermore, while prior studies on interpretable saliency maps
Video diffusion models can generate visually stunning content, yet frequently produce motion that violates physical laws, objects accelerate implausibly or vanish mid-trajectory. We reveal a surprising finding: a 2-step generation often exhibits better physical consistency than a 50-step output from…
Generating high-quality novel views of a scene from a single image requires maintaining structural coherence across different views, referred to as view consistency.While diffusion models have driven advancements in novel view synthesis, they still struggle to preserve spatial continuity across view…