Sangpil Kim

15

Papers

74

Total Citations

Papers (15)

WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights

SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting

3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation

CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection

CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image

Cropper: Vision-Language Model for Image Cropping through In-Context Learning

PASTA: Part-Aware Sketch-to-3D Shape Generation with Text-Aligned Prior

Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning

Insightful Instance Features for 3D Instance Segmentation

Active Test-time Vision-Language Navigation

EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting

FaceShield: Defending Facial Image against Deepfake Threats

Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior

3D-GSW: 3D Gaussian Splatting for Robust Watermarking

Higher-order Relational Reasoning for Pedestrian Trajectory Prediction