Building Design + Construction

Innovations from the nation’s largest engineering firms

Photo: Jeremiah Hull Photography, courtesy WSP Of the 100+ engineering and engineering/architecture firms that participated ...
IEEE

LSV-MAE: A Masked-Autoencoder Pre-Training Approach for Large-Scale 3D Point Cloud Data

Abstract: Masked language modeling (MLM) and masked image modeling (MIM) pretraining paradigms have achieved remarkable success in both natural language processing (NLP) and computer vision (CV).
IEEE

Stitching, Fine-Tuning, and Re-Training: A SAM-Enabled Framework for Semi-Supervised 3D Medical Image Segmentation

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost ...
GitHub

The repo for ``3D Plant Phenotyping from a Single Image: Generalizable Plant Monocular Depth Estimation via Dataset Mixing''.

PlantDepth/ ├── Crops3D/ # Sub-dataset ├── depth/ # Depth maps ├── rgb/ # RGB images ├── segmentation/ # Segmentation labels ├── test_file_list.txt # List of test files used for evaluation ├── ...
GitHub

FastGS: Training 3D Gaussian Splatting in 100 Seconds

Note: The Conda CUDA and system CUDA versions may differ. The compiler version (nvcc) is what matters for PyTorch extensions compilation (diff-gaussian-rasterization_fastgs). The MipNeRF360 scenes are ...