NeuralFusion

This is the official implementation of NeuralFusion: Online Depth Map Fusion in Latent Space. We provide code to train the proposed pipeline on ShapeNet, ModelNet, as well as Tanks and Temples.

If you plan to use NeuralFusion for commercial purposes, please contact the author first. For more information, please also see the license.

Installation

Install the code using the following steps

conda env create -f environment.yml
conda activate neural-fusion

Data Preparation

In order to prepare the data, please follow the instructions explained in this repo.

Training

In order to train the pipeline, run the following

python train.py --experiment_path /path/where/you/want/to/save/the/experiment \ 
                --data_path /path/to/your/data \
                --config configs/train/your/config.yaml

Testing

In order to test the pipeline, run the following

python test.py --test /path/to/your/test/config \
               --root_path /path/where/you/saved/your/experiments \
               --data_path /path/to/your/data \
               --experiment $experiment_name \ 
               --version $experiment_version \
               --checkpoint $experiment_checkpoint

For example, if you would like to test the pretrained on ShapeNet, you need to run the following command

export DATA_PATH=/path/to/your/preprocessed/shapenet/data


python test.py --test configs/test/shapenet/shapenet.noise.005.yaml \
               --root_path pretrained_models \
               --data_path $DATA_PATH \
               --experiment shapenet_noise_005 \ 
               --version 0 \
               --checkpoint best.ckpt

Official implementation of NeuralFusion: Online Depth Map Fusion in Latent Space

Related tags

Overview

NeuralFusion

Installation

Data Preparation

Training

Testing

Owner

Github for the conference paper GLOD-Gaussian Likelihood OOD detector

A simplified framework and utilities for PyTorch

Per-Pixel Classification is Not All You Need for Semantic Segmentation

Probabilistic Tensor Decomposition of Neural Population Spiking Activity

Tello Drone Trajectory Tracking

Code for pre-training CharacterBERT models (as well as BERT models).

Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).

Language Models for the legal domain in Spanish done @ BSC-TEMU within the "Plan de las Tecnologías del Lenguaje" (Plan-TL).

A wrapper around SageMaker ML Lineage Tracking extending ML Lineage to end-to-end ML lifecycles, including additional capabilities around Feature Store groups, queries, and other relevant artifacts.

Attentional Focus Modulates Automatic Finger‑tapping Movements

Code for "Solving Graph-based Public Good Games with Tree Search and Imitation Learning"

Hysterese plugin with two temperature offset areas

Structured Data Gradient Pruning (SDGP)

Code accompanying "Adaptive Methods for Aggregated Domain Generalization"

A production-ready, scalable Indexer for the Jina neural search framework, based on HNSW and PSQL

sequitur is a library that lets you create and train an autoencoder for sequential data in just two lines of code

Official Pytorch implementation of Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (ICLR 2022)

Code and real data for the paper "Counterfactual Temporal Point Processes", available at arXiv.

RIM: Reliable Influence-based Active Learning on Graphs.

SwinTrack: A Simple and Strong Baseline for Transformer Tracking