Jin-Wei Chen

Immersive AR/VR experiences can finally have stereo audio that dynamically tracks visual sources, thanks to a novel framework that binds visual motion to sound localization.

WildSplat achieves state-of-the-art novel view synthesis from unposed images by effectively decoupling geometry and appearance, even under challenging lighting conditions.

Ditch the clunky external tools: VeraRetouch slashes model size and unlocks end-to-end training for photo retouching with a fully differentiable architecture.

Forget tedious manual adjustments: SmartPhotoCrafter automatically enhances photos by reasoning about image quality and generating targeted edits.

Forget small-scale image editing datasets – this work unleashes a million-scale human preference dataset that unlocks better reward models and boosts text-guided image editing performance.