REVIEW 4 cited by
Find Any Part in 3D
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Why don't we have foundation models in 3D yet? A key limitation is data scarcity. For 3D object part segmentation, existing datasets are small in size and lack diversity. We show that it is possible to break this data barrier by building a data engine powered by 2D foundation models. Our data engine automatically annotates any number of object parts: 1755x more unique part types than existing datasets combined. By training on our annotated data with a simple contrastive objective, we obtain an open-world model that generalizes to any part in any object based on any text query. Even when evaluated zero-shot, we outperform existing methods on the datasets they train on. We achieve 260% improvement in mIoU and boost speed by 6x to 300x. Our scaling analysis confirms that this generalization stems from the data scale, which underscores the impact of our data engine. Finally, to advance general-category open-world 3D part segmentation, we release a benchmark covering a wide range of objects and parts. Project website: https://ziqi-ma.github.io/find3dsite/
Forward citations
Cited by 4 Pith papers
-
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
-
DexVLG: Dexterous Vision-Language-Grasp Model at Scale
DexVLG is a vision-language model trained on 170 million simulated dexterous grasps that generates hand poses aligned with language instructions about which part of an object to grasp.
-
UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation
UAD distills affordance knowledge from vision-language models and DINOv2 features into a lightweight task-conditioned model that predicts pixel-level manipulation regions and improves few-shot imitation learning gener...
-
OpenHuman4D: Open-Vocabulary 4D Human Parsing
OpenHuman4D combines a video tracker with mask validation and attention-based embedding fusion to deliver fast, text-queryable segmentation of 4D human videos.
Discussion (0). Continue with ORCID to comment.