Views
No views yet
<scene>/
├── cfg_args # training configuration
├── cameras.json # camera parameters
├── input.ply # initial point cloud
├── results.json, per_view.json # evaluation metrics
├── events.out.tfevents.* # training log (TensorBoard)
└── point_cloud/iteration_30000/
├── point_cloud_state_dict.pt # trained DETRIS primitives
└── hyperparameters.pt1# 1. clone the code
2git clone --recursive https://github.com/orioljim1/detris
3cd detris
4
5# 2. download & extract this release
6# (e.g. with the huggingface_hub CLI)
7hf download Orioljim/detris-models detris_models.zip --local-dir .
8unzip detris_models.zip
9
10# 3. render a scene (see the code repo README for full options)
11python render.py -m main_results/mipnerf360/gardenLICENSE.md in the code repository.1@inproceedings{JimenezAyguade2026Deformable,
2 title = {Deformable Triangle Splatting: Flexible Primitives for Real-Time Radiance Field Rendering},
3 author = {Jiménez-Ayguadé, Oriol and Agudo, Antonio},
4 booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
5 year = {2026},
6}