Wenqi Xian

11

Papers

79

Total Citations

Papers (11)

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset

FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution

Self-Calibrating Gaussian Splatting for Large Field-of-View Reconstruction

TextureGAN: Controlling Deep Image Synthesis With Texture Patches

BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

Stay Positive: Non-Negative Image Synthesis for Augmented Reality

Space-Time Neural Irradiance Fields for Free-Viewpoint Video

Neural Lens Modeling

UprightNet: Geometry-Aware Camera Orientation Estimation From Single Images

Crowdsampling the Plenoptic Function