shawLyu
Follow
Stars
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
iDisc: Internal Discretization for Monocular Depth Estimation [CVPR 2023]
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction
[ICCV 2023 Oral] ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes
[WACV 2025] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
TartanAir dataset tools and samples
A Scalable Pipeline for Making Steerable Multi-Task Mid-Level Vision Datasets from 3D Scans [ICCV 2021]
Universal Monocular Metric Depth Estimation
[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
A differentiable point-based rendering framework.
Official Code for MotionCtrl [SIGGRAPH 2024]
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
Taming Transformers for High-Resolution Image Synthesis
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
A plugin for GTAV that transforms it into a vision-based self-driving car research environment.
Gaussian Splatting from VGGSfM and Mast3r, and their comparison
🔄 [ECCV‘24] Pytorch implementation of 'Surface Reconstruction from 3D Gaussian Splatting via Local Structural Hints'
🏠 [ECCV 2024] Pytorch implementation of 'HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression'
an unofficial 2DGS implementation based on GauStudio
[AAAI 2025] DepthFM: Fast Monocular Depth Estimation with Flow Matching
GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models
Ongoing research training gaussian splatting at scale by distributed system