nerfstudio-gnt

Unofficial GNT (Generalizable NeRF Transformer) integration for Nerfstudio.

Install

uv pip install -e .

Verify method registration

ns-train --help | grep -i gnt

Dataset format

This integration uses Nerfstudio's native VanillaDataManager with NerfstudioDataParserConfig. Point the dataparser to a scene root containing transforms.json.

Configure GNT

Basic Training (Full Network Training - Default)

By default, all components (ResUNet feature extractor and GNT transformer network) are fully trainable (freeze_mode = "none"):

ns-train gnt --pipeline.datamanager.data-root /path/to/datasets

Transfer Learning & Freezing Strategies

When initializing with pretrained weights (or transferring priors across distinct image domains such as histology datasets), you can specify how the feature network is frozen via --pipeline.model.freeze_mode:

Full Training (none - Default):

ns-train gnt \
  --pipeline.datamanager.dataparser.data /path/to/scene_root \
  --pipeline.model.transfer_learning True \
  --pipeline.model.pretrained_ckpt_path /path/to/pretrained.pth \
  --pipeline.model.freeze_mode none

Freeze Late Layers (late): Keeps the ResNet encoder (conv1, bn1, layer1, layer2, layer3) trainable to adapt to domain-specific low-level image distributions (e.g. histology), while freezing the U-Net decoder (upconv3, iconv3, upconv2, iconv2, out_conv):

ns-train gnt \
  --pipeline.datamanager.dataparser.data /path/to/scene_root \
  --pipeline.model.transfer_learning True \
  --pipeline.model.pretrained_ckpt_path /path/to/pretrained.pth \
  --pipeline.model.freeze_mode late

Freeze Early Layers (early): Freezes the ResNet encoder backbone (conv1, bn1, layer1, layer2, layer3) and trains only the U-Net decoder:

ns-train gnt \
  --pipeline.datamanager.dataparser.data /path/to/scene_root \
  --pipeline.model.transfer_learning True \
  --pipeline.model.pretrained_ckpt_path /path/to/pretrained.pth \
  --pipeline.model.freeze_mode early

Freeze All Extractor Weights (all): Freezes the entire ResUNet feature network:

ns-train gnt \
  --pipeline.datamanager.dataparser.data /path/to/scene_root \
  --pipeline.model.transfer_learning True \
  --pipeline.model.pretrained_ckpt_path /path/to/pretrained.pth \
  --pipeline.model.freeze_mode all

Differential Learning Rates

You can configure different learning rates for the feature network and transformer networks via CLI optimizer flags:

ns-train gnt \
  --pipeline.datamanager.dataparser.data /path/to/scene_root \
  --pipeline.model.transfer_learning True \
  --optimizers.feature_net.optimizer.lr 5e-5 \
  --optimizers.network.optimizer.lr 5e-4

Smoke check

python test.py /path/to/scene_root/transforms.json

This runs one train step through GNTPipeline.get_train_loss_dict and checks source-view tensor shapes.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nerfstudio_gnt-0.0.29.tar.gz (60.3 kB view details)

Uploaded Sep 1, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

nerfstudio_gnt-0.0.29-py3-none-any.whl (83.1 kB view details)

Uploaded Sep 1, 2026 Python 3

File details

Details for the file nerfstudio_gnt-0.0.29.tar.gz.

File metadata

Download URL: nerfstudio_gnt-0.0.29.tar.gz
Upload date: Sep 1, 2026
Size: 60.3 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Arch Linux","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for nerfstudio_gnt-0.0.29.tar.gz
Algorithm	Hash digest
SHA256	`7c8addb30ba2e91a5a8719c9781ba0b1b7786e65618a04727b9d36eb2cd42cf5`
MD5	`e894c9eae9736545e17bbf05b32d5672`
BLAKE2b-256	`8b731d35f7384b0f0b160555671c65af3a739f15870cc2f2cff40dc1f7cf2a45`

See more details on using hashes here.

File details

Details for the file nerfstudio_gnt-0.0.29-py3-none-any.whl.

File metadata

Download URL: nerfstudio_gnt-0.0.29-py3-none-any.whl
Upload date: Sep 1, 2026
Size: 83.1 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Arch Linux","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for nerfstudio_gnt-0.0.29-py3-none-any.whl
Algorithm	Hash digest
SHA256	`7de4a68eb026abb1dc9413fa9402b71d389caec29505b7e9c0ed9617784dbfbe`
MD5	`42240ffb787c503c8a8b078631a68f8b`
BLAKE2b-256	`d001bd54bff8ba0f27df928c1632ba7d0c2476e6bf18731ad7f67fe24f268b01`