-
Virginia Tech
- Fulls Church, Virginia
Highlights
- Pro
Starred repositories
[CVPR 2024 Highlight] Official repository for the paper "3DGStream: On-the-fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos".
A general fine-tuning kit geared toward diffusion models.
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
A 3DGS framework for omni urban scene reconstruction and simulation.
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
[ECCV'24] FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information
[CVPR2024] NeuRAD: Neural Rendering for Autonomous Driving
PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
[ECCV2024 Oral] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow
a generalist algorithm for cellular segmentation with human-in-the-loop capabilities
Open-Sora: Democratizing Efficient Video Production for All
Scripts for building, training and validating CNNs for Connectomics
Repository of model architectures and network weights used for CellMap segmentations.
Data annotation toolbox supports image, audio and video data.
A differentiable point-based rendering framework.
A modular differential gaussian rasterization library.
Using Low-rank adaptation to quickly fine-tune diffusion models.
Fine-Grained Open Domain Image Animation with Motion Guidance
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton