3d-objects
sample_3d_objects
Urban3D Dataset (Sample)
This is a sample subset of the Urban3D dataset, demonstrating the structure and format of our large-scale collection of real-world, object-centric multiview videos and 3D reconstructions for advancing machine learning research in autonomous systems, smart infrastructure, and urban scene understanding.
Dataset Overview
This sample includes select examples from our dataset which contains:
10,000+ multiview videos across urban categories
Categories… See the full description on the dataset page: https://huggingface.co/datasets/zeroframe/sample_3d_objects.Day_to_Day_Objects_isometric_skeumorphic_3d_bnbBuilt with https://huggingface.co/spaces/aisheets/sheets
and this config:
columns:
object_name:
modelName: meta-llama/Llama-3.3-70B-Instruct
modelProvider: groq
userPrompt: Generate the name of a common day to day object
prompt: >
You are a rigorous text-generation engine. Generate only the requested
output format, with no explanations following the user instruction and
avoiding repetition of the existing responses at the end of the prompt.
# User… See the full description on the dataset page: https://huggingface.co/datasets/aisheets/Day_to_Day_Objects_isometric_skeumorphic_3d_bnb.multilingual-crossmodal-conflict-3D_Objects3D-Objects-Detection
3D Object Detection Dataset
Overview
Data type: LiDAR (point clouds) + Camera (RGB images)
Size: 245.7 GB, 1,194 ZIP archives
Files: 61,480 PCD + 3,619 JPG
Annotations: 735,483 3D bounding boxes
Sessions: 101 unique recording sessions
Camera resolution: 2880×1860
Structure
.
├── README.md
├── merged_result.parquet # Main annotation table
├── tf.parquet # Transform tree
├── camera_info.parquet # Camera… See the full description on the dataset page: https://huggingface.co/datasets/StarLineResearch/3D-Objects-Detection.dataset_sam-3d-objectsmultilingual-crossmodal-conflict-3D_Objects
Multilingual Cross-Modal Conflict — 3D Objects
A multilingual counterfactual MCQ dataset built from rendered 3D object scenes.
Each row contains a rendered 3D scene image, two captions (original vs counterfactual), and a multiple-choice question probing whether a VLM follows the image or the misleading text.
Languages
Language
Code
Rows
English
en
150
Hindi
hi
150
Telugu
te
150
Bahasa Indonesia
id
150
Columns
Column
Type… See the full description on the dataset page: https://huggingface.co/datasets/apart-global-south-hack/multilingual-crossmodal-conflict-3D_Objects.