- Mapo-gu, Korea
- https://www.linkedin.com/in/seunghyunss
- @sseunghyunss
Stars
Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Image (NeurIPS 2024)
[ECCV 2024] GenPose++: A generative category-level 6D object pose estimation and tracking approach proposed in Omni6DPose.
[ECCV 2024] Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking
Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.
CVPR2024: Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation
code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503
Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation (Accepted by NeurIPS-2023)
Auto-encoding & Generating 3D Point-Clouds.
Self-Supervised Learning for Domain Adaptation on Point-Clouds
[ICCV '21] "Unsupervised Point Cloud Pre-training via Occlusion Completion"
(ICCV2023) IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
PyTorch implementation of Pointnet2/Pointnet++
Research report on 6D pose estimation
[CVPR 2024] Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)
A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion
(TPAMI 2023) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
Papers and Datasets about Point Cloud.
Experiments on unsupervised point cloud reconstruction.
Geometric Latent Diffusion Models for 3D Molecule Generation