Youshaa Murhij's starred repositories
AnimateDiff
Official implementation of AnimateDiff.
Torch-Pruning
[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
StreamPETR
[ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
DrivingDiffusion
Layout-Guided multi-view driving scene video generation with latent diffusion model
superpoint_transformer
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering"
BEVFormer_tensorrt
BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).
SphereFormer
The official implementation for "Spherical Transformer for LiDAR-based 3D Recognition" (CVPR 2023).
SOLOFusion
Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection
bevdet-tensorrt-cpp
BEVDet implemented by TensorRT, C++; Achieving real-time performance on Orin
CUDA-FastBEV
TensorRT deploy and PTQ/QAT tools development for FastBEV, total time only need 6.9ms!!!
LargeKernel3D
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)
FocalFormer3D
Official PyTorch implementation of FocalFormer3D [ICCV 2023]
DSVT-AI-TRT
DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets(CVPR2023),vaymo vehicle 3D Object Detection(top2), waymo cyclist 3D Object Detection(top1),waymo pedestrian 3D Object Detection(top1)
Rock-Track
Official Repo For "RockTrack"
WACV23_PIDS-Joint-Point-Interaction-Dimension-Search-for-3D-Point-Cloud
Open source code for Paper: "PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud".
CUDA-PointPillars-ROS2
A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar. Deploying to ROS2 system. Forked from NVIDIA's repo.