-
NAVER LABS
- Seongnam, South Korea
- in/hyeontae-son-933691152
- https://scholar.google.com/citations?user=krYfI4AAAAAJ
Highlights
- Pro
Starred repositories
Original implementaion of "Radiant Foam: Real-Time Differentiable Ray Tracing"
[ICLR 2025] Official implementation of "DiffSplat: Repurposing Image Diffusion Models for Scalable 3D Gaussian Splat Generation".
Official implementation of Continuous 3D Perception Model with Persistent State
🚀 Strapi is the leading open-source headless CMS. It’s 100% JavaScript/TypeScript, fully customizable, and developer-first.
File format for 3D Gaussian splats. About 10x smaller than the PLY equivalent with virtually no perceptible loss in visual quality. Offered as open source by Niantic Labs. More details at https://s…
Efficient and parallel algorithms for point cloud registration [C++, Python]
Official implementation of "SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization" (ECCV 2024)
Official implimentation for EVA-Gaussian: 3D Gaussian-Based Real-time Human Novel View Synthesis Under Diverse Camera Settings
Official Pytorch implementation for "IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION" [ICLR 2025]
Source Code for SIGGRAPH 2023 Paper "Parameter-space ReSTIR for Differentiable and Inverse Rendering"
Fully open reproduction of DeepSeek-R1
A collection of GICP-based fast point cloud registration algorithms
💪 [ARXIV 2025] Pytorch implementation of 'HAC++: Towards 100X Compression of 3D Gaussian Splatting'
CUDA Python: Performance meets Productivity
FlashInfer: Kernel Library for LLM Serving
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
PhyRecon: Physically Plausible Neural Scene Reconstruction
A diffusion model-based stereo depth estimation framework that can predict state-of-the-art depth and restore noisy depth maps for transparent and specular surfaces
[CVPR2024] NTO3D: Neural Target Object 3D Reconstruction with Segment Anything
[ECCV'24] On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy
[PyTorch] Official implementation of CVPR2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency". https://arxiv.org/abs/2103.05465