Seungryong Kim

21

Papers

146

Total Citations

Papers (21)

DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization

Unifying Correspondence Pose and NeRF for Generalized Pose-Free Novel View Synthesis

FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking

Emergent Temporal Correspondences from Video Diffusion Transformers

Seurat: From Moving Points to Depth

Context Enhanced Transformer for Single Image Object Detection in Video Data

Visual Persona: Foundation Model for Full-Body Human Customization

ControlFace: Harnessing Facial Parametric Control for Face Rigging

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models

Few-Shot Neural Radiance Fields under Unconstrained Illumination

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation

Identity-preserving Distillation Sampling by Fixed-Point Iterator

Retrieval-Augmented Score Distillation for Text-to-3D Generation

Exploring Temporally-Aware Features for Point Tracking

Cross-View Completion Models are Zero-shot Correspondence Estimators

Mixture of Submodules for Domain Adaptive Person Search

AM-Adapter: Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis in-the-Wild

S⁴M: Boosting Semi-Supervised Instance Segmentation with SAM

Active Test-time Vision-Language Navigation

MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation

Multi-Granularity Video Object Segmentation