This repository is a Pytorch porting of the Escoin-caffe Sparse Convolution implementation.
3D Shape Completion using EDM Diffusion on Sparse Signed Distance Fields.
NVIDIA/MinkowskiEngine ported to torch 2.11 / CUDA 12.8 / CCCL 2.x: builds and runs on sm_89 + sm_120 (Blackwell), 48 errors to 0
Lidar Bridge Classification
Lidar Bridge Classification
Efficient convolution for sparse data on FPGAs
Sparse ConvLSTM for Point Cloud Semantic Segmentation
An implementation of Sparse Layers in TensorFlow 2. x.
TSC-PCAC: Voxel Transformer and Sparse Convolution Based Point Cloud Attribute Compression for 3D Broadcasting
spconv-Triton is a fast sparse convolution library with full operator support (SubM conv, Conv3D, Transposed Conv, Pooling). It is hardware-agnostic and runs on GPUs supporting Triton.
Open Source Project for 3D Semantic Segmentation
Fork of NVIDIA MinkowskiEngine modernized for CUDA 12.8+/Blackwell (RTX 50-series), NumPy 2.0, PyTorch 2.x prebuilt wheels, fp16/bf16 autocast, fused gather/scatter. Best-effort, no support commitment.
[WACV'25] Official implementation of "PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplane MRI Slices".
Dynamic Frame Interpolation in Wavelet Domain (TIP 2023)
Neural Medial Axis Approximation of Point Clouds for 3D Tree Skeletonization
[IROS 2020] Indoor Scene Recognition in 3D
Unofficial PyTorch implementation of the paper: "CenterNet3D: An Anchor free Object Detector for Autonomous Driving"
[CVPR24] MaGGIe: Mask Guided Gradual Human Instance Matting
[ECCV 2024] 3D Small Object Detection with Dynamic Spatial Pruning
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution (CVPR 2023)
To associate your repository with the sparse-convolution topic, visit your repo's landing page and select "manage topics."