Ke Xian

14

Papers

10

Total Citations

Papers (14)

Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix

S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes

Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering

DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video

Monocular Relative Depth Perception With Web Stereo Data Supervision

Structure-Guided Ranking Loss for Single Image Depth Prediction

Composing Photos Like a Photographer

BokehMe: When Neural Rendering Meets Classical Rendering

3D Cinemagraphy From a Single Image

When Unsupervised Domain Adaptation Meets Tensor Representations

Neural Video Depth Stabilizer

Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction

PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects