Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

aminebdj/ScanEdit

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

5 Commits

Repository files navigation

SCANEDIT Inference

πŸ“‹ Overview

SCANEDIT is a 3D scene editing framework that uses language models to understand and execute scene manipulation tasks based on text prompts.

βœ… Project Status

Completed βœ“

  • Inference code released
  • Installation scripts
  • Documentation

TODO 🚧

  • Inference sample
  • Evaluation setup
  • Evaluation data

πŸš€ Quick Start

Installation

# Clone the repository
git clone https://github.com/aminebdj/ScanEdit
cd ScanEdit
# Run the installation script
chmod +x install_environment.sh
./install_environment.sh
# Activate the environment
conda activate scanedit

Set up API Key

export GROQ_API_KEY="your_api_key_here"

πŸ’» Usage

Complete Example

SCENE_NAME="3e8bba0176"
python inference.py \
 --scene_name "$SCENE_NAME" \
 --text_prompt "Create a seating area for a lecture on the whiteboard" \
 --path_to_ply "/data/scannetpp/plys/validation/${SCENE_NAME}.ply" \
 --masks_classes_path "/data/scannetpp/semantic_3d_masks/${SCENE_NAME}.pt" \
 --path_to_rgb_data "/data/scannetpp/data/${SCENE_NAME}/dslr/undistorted_images" \
 --path_to_2d_masks "/data/scannetpp/undistorted_rast_masks/${SCENE_NAME}.pt" \
 --path_to_annotations "/data/scannetpp/vlm_annotations/${SCENE_NAME}.yaml" \
 --dataset "scannetpp" \
 --llm_name "openai/gpt-oss-120b" \
 --folder_name "results" \
 --output_dir "./outputs" \
 --verbose

πŸ”§ Arguments Reference

Click to expand full argument list

Paths

  • --path_to_rgb_data: RGB images directory
  • --path_to_2d_masks: 2D projection masks (.pt)
  • --path_to_annotations: VLM annotations (.yaml)
  • --path_to_save_additional_masks: Output path for masks
  • --img_sample_path: Sample image for testing

Model Configuration

  • --groq_api_key: GROQ API key (default: env var)
  • --llm_name: LLM model name (default: "openai/gpt-oss-120b")
  • --dataset: Dataset type (choices: scannetpp, replica)

Output Settings

  • --folder_name: Output subdirectory name
  • --output_dir: Base output directory
  • --device: Computation device (cuda/cpu)

Flags

  • --use_preds: Use predicted masks (adds extension)
  • --verbose: Enable detailed logging

πŸ“ Dataset Structure

project_root/
β”œβ”€β”€ data/
β”‚ └── scannetpp/
β”‚ β”œβ”€β”€ data/
β”‚ β”‚ └── {scene_name}/
β”‚ β”‚ └── dslr/
β”‚ β”‚ └── undistorted_images/
β”‚ β”‚ β”œβ”€β”€ DSC00001.JPG
β”‚ β”‚ └── ...
β”‚ β”œβ”€β”€ plys/
β”‚ β”‚ └── validation/
β”‚ β”‚ β”œβ”€β”€ 3e8bba0176.ply
β”‚ β”‚ └── ...
β”‚ β”œβ”€β”€ undistorted_rast_masks/
β”‚ β”‚ └── {scene_name}.pt
β”‚ β”‚
β”‚ β”œβ”€β”€ semantic_3d_masks/
β”‚ β”‚ └── {scene_name}.pt
β”‚ β”‚ 
β”‚ └── vlm_annotations/
β”‚ └── {scene_name}.yaml
β”‚
└── outputs/
 └── {folder_name}/
 └── {scene_name}/
 β”œβ”€β”€ final.ply
 └── ...

πŸ“š Citation

@inproceedings{el2025scanedit,
 title={ScanEdit: Hierarchically-Guided Functional 3D Scan Editing},
 author={El Amine Boudjoghra, Mohamed and Laptev, Ivan and Dai, Angela},
 booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
 pages={27105--27115},
 year={2025}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

AltStyle γ«γ‚ˆγ£γ¦ε€‰ζ›γ•γ‚ŒγŸγƒšγƒΌγ‚Έ (->γ‚ͺγƒͺγ‚ΈγƒŠγƒ«) /