Junhwa Hur

15

Papers

11

Total Citations

Papers (15)

Emergent Temporal Correspondences from Video Diffusion Transformers

Toward Material-Agnostic System Identification from Videos

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

WonderJourney: Going from Anywhere to Everywhere

Generalized Deformable Spatial Pyramid: Geometry-Preserving Dense Correspondence Estimation

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation

Self-Supervised Monocular Scene Flow Estimation

Self-Supervised Multi-Frame Monocular Scene Flow

Self-Supervised AutoFlow

MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation

Motion Prompting: Controlling Video Generation with Motion Trajectories

High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion

Self-supervised surround-view depth estimation with volumetric feature fusion

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence