📊
Steer3d Data dataset by ziqima
⭐ 32.9
📊
Dataset

Steer3d Data

by ziqima hf-dataset--ziqima--steer3d-data
Nexus Index
32.9 Top 100%
S: Semantic 50
A: Authority 0
P: Popularity 56
R: Recency 52
Q: Quality 30
Tech Context
Vital Performance
0 DL / 30D
0.0%
Source →
Data Integrity 32.9 FNI Score
- Size
- Rows
Parquet Format
- Tokens
Dataset Information Summary
Entity Passport
Registry ID hf-dataset--ziqima--steer3d-data
License MIT
Provider huggingface
📜

Cite this dataset

Academic & Research Attribution

BibTeX 
@misc{hf_dataset__ziqima__steer3d_data,
  author = {ziqima},
  title = {Steer3d Data Dataset},
  year = {2026},
  howpublished = {\url{https://huggingface.co/datasets/ziqima/steer3d-data}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}
APA Style
ziqima. (2026). Steer3d Data [Dataset]. Free2AITools. https://huggingface.co/datasets/ziqima/steer3d-data

đŸ”ŦTechnical Deep Dive

Full Specifications [+]

⚖ī¸ Nexus Index V2.0

Methodology Index Protocol
32.9
TOP 100% SYSTEM IMPACT
Semantic (S) 50
Authority (A) 0
Popularity (P) 56
Recency (R) 52
Quality (Q) 30

đŸ’Ŧ Index Insight

FNI V2.0 for Steer3d Data: Semantic (S:50), Authority (A:0), Popularity (P:56), Recency (R:52), Quality (Q:30).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit
Unbiased Data Node Refresh: VFS Live
âŦ‡ī¸
Downloads
74,150

👁ī¸ Data Preview

📊

Row-level preview not available for this dataset.

Schema structure is shown in the Field Logic panel when available.

🔗 Explore Full Dataset ↗

đŸ§Ŧ Field Logic

đŸ§Ŧ

Schema not yet indexed for this dataset.

Dataset Specification

Steer3D Training Data

This repository contains the training data for the paper Feedforward 3D Editing via Text-Steerable Image-to-3D.

Project Page: https://glab-caltech.github.io/steer3d/ Code: https://github.com/ziqi-ma/Steer3D

The metadata directory contains training metadata used for texture, removal, and addition. data/images contains the input images, identified by a unique uuid for each object. We release TRELLIS latents of all source and target assets in data/latents, also identified by the uuid.

Sample Usage

This dataset is used to train the Steer3D model. Below are examples of how to train Stage 1 and Stage 2 of the model using this dataset, adapted from the GitHub repository.

First, ensure your PYTHONPATH is set to the root directory of the Steer3D repository:

bash 
export PYTHONPATH=[path to Steer3D]

Flow-matching training of Stage 1:

bash 
python trainers/train_stage1.py --config configs/stage1_controlnet.json --output_dir outputs/stage1

Flow-matching training of Stage 2:

bash 
python trainers/train_stage2.py --config configs/stage2_controlnet.json --output_dir outputs/stage2

DPO of Stage 2:

bash 
python trainers/train_stage2.py --config configs/stage2_dpo.json --output_dir outputs/stage2dpo

Finetuning Stage 1 backbone:

bash 
python trainers/train_stage1_backbone.py \
        --config configs/stage1_base_sft.json \
        --output_dir outputs/stage1_sft

Social Proof

HuggingFace Hub
74.2KDownloads
Hub Discussions
🤗 Data Source: Hugging Face ↗
🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹī¸ Verify with original source

🛡ī¸ Dataset Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id
hf-dataset--ziqima--steer3d-data
slug
ziqima--steer3d-data
source
huggingface
author
ziqima
license
MIT
tags
task_categories:image-to-3d, license:mit, modality:image, arxiv:2512.13678, region:us, 3d-editing, text-to-3d

⚙ī¸ Technical Specs

architecture
null
params billions
null
context length
null
pipeline tag

📊 Engagement & Metrics

downloads
74,150
stars
0
forks
0

Data indexed from public sources. Updated daily.