Gim Hee Lee

Segment Any Events with Language

LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding

Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and Generation

Semi-3DETR: Semi-Supervised Detection Transformer for 3D Object Detection

EventSR-Zero: Training-free Event Video Super-Resolution with Diffusion Priors

MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction

WorldCrafter: Dynamic Scene Generation from a Single Image with Geometric and Temporal Consistency

Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation

Distil-E2D: Distilling Image-to-Depth Priors for Event-Based Monocular Depth Estimation

PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis

Event-Driven Dynamic Scene Depth Completion

X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability

ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors

Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding

Segment Any 3D Object with Language

4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos

Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting

GenXD: Generating Any 3D and 4D Scenes

Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory Prediction

Generalizable Human Gaussians from Single-View Image

FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies

Event Camera Object Detection at Arbitrary Frequencies

econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians

Event-aided Dense and Continuous Point Tracking