Gim Hee Lee

75

Papers

263

Total Citations

Papers (75)

Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering

Line-Sweep: Cross-Ratio For Wide-Baseline Matching and 3D Reconstruction

TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

Relative Pose Estimation of Calibrated Cameras with Known SE(3) Invariants

GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency

GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields

g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks

MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation

Learnable Infinite Taylor Gaussian for Dynamic View Rendering

TreeSBA: Tree-Transformer for Self-Supervised Sequential Brick Assembly

STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene

Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data

DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF

ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation

Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption

Sparse to Dense 3D Reconstruction From Rolling Shutter Images

PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition

Baseline Desensitizing in Translation Averaging

Solving the Perspective-2-Point Problem for Flying-Camera Photo Composition

Convolutional Sequence to Sequence Model for Human Dynamics

CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization

SO-Net: Self-Organizing Network for Point Cloud Analysis

Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes

Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network

Cascaded Refinement Network for Point Cloud Completion

Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels

RPM-Net: Robust Point Matching Using Learned Features

SESS: Self-Ensembling Semi-Supervised 3D Object Detection

DeepI2P: Image-to-Point Cloud Registration via Deep Classification

From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation

Multi-View Multi-Person 3D Pose Estimation With Plane Sweep Stereo

Few-Shot 3D Point Cloud Semantic Segmentation

REGTR: End-to-End Point Cloud Correspondences With Transformers

Novel Class Discovery in Semantic Segmentation

DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields

ScarceNet: Animal Pose Estimation With Scarce Annotations

Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction

ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning

NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects

Rolling-Shutter-Aware Differential SfM and Image Rectification

USIP: Unsupervised Stable Interest Point Detection From 3D Point Clouds

Transferable Semi-Supervised 3D Object Detection From RGB-D Data

Voxel-Based Network for Shape Completion by Leveraging Edge Generation

MINE: Towards Continuous Depth MPI With NeRF for Novel View Synthesis

GeT: Generative Target Structure Debiasing for Domain Adaptation

Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion

Unsupervised Feature Representation Learning for Domain-generalized Cross-domain Image Retrieval

Generalized Few-Shot Point Cloud Segmentation via Geometric Words

Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data

Weakly-supervised 3D Pose Transfer with Keypoints

Optimizing the Placement of Roadside LiDARs for Autonomous Driving

Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry

HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization

Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation

Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion

Rethinking IoU-Based Optimization for Single-Stage 3D Object Detection

Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

Feature Representation Learning for Unsupervised Cross-Domain Image Retrieval

DReg-NeRF: Deep Registration for Neural Radiance Fields

DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splatting

IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments

Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning

DuCos: Duality Constrained Depth Super-Resolution via Foundation Model

PS-Mamba: Spatial-Temporal Graph Mamba for Pose Sequence Refinement

Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images

Street Gaussians without 3D Object Tracker

Event-aided Dense and Continuous Point Tracking: Everywhere and Anytime

LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs

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

NeurIPS 2025arXiv

Coarse-to-fine Animal Pose and Shape Estimation

Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection

Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation

GNeSF: Generalizable Neural Semantic Fields

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF