AI Paper Atlas

Research map / 3D vision / 3D generation

PartField: Learning 3D Feature Fields for Part Segmentation and Beyond

Minghua Liu, Mikaela Angelina Uy, Donglai Xiang, Hao Su, Sanja Fidler, Nicholas Sharp, Jun Gao

ICCV 2025 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 61 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add PartNet 3D part labels as extra training triplets (ablation)PartField (Objaverse 2D proposals) · PartObjaverse-TinymIoU: 77.70 -> 77.90Improved
add hard negative sampling (ablation)PartField (Objaverse 2D proposals) · PartObjaverse-TinymIoU: 77.70 -> 78.90Improved
add hard negative sampling to Objaverse+PartNet (ablation)PartField · PartObjaverse-TinymIoU: 77.90 -> 79.20Improved
add PartNet triplets on top of hard negative sampling (ablation)PartField · PartObjaverse-TinymIoU: 78.90 -> 79.20Improved
use PartField instead of second-best SAMeshSAMesh · PartObjaverse-TinymIoU: 56.86 -> 79.18Improved
use PartField instead of SAMPart3DSAMPart3D · PartNetE test (1906 shapes)mIoU: 56.17 -> 59.10Improved
use feedforward model instead of per-shape optimizationSAMPart3D · PartObjaverse-Tinyruntime: ~15min -> ~10sImproved
use text-free 3D feature field instead of text-input methodsPartSLIP/Find3D · PartObjaverse-TinymIoU: 31.54 -> 79.18Improved

Later papers that compared with this method

7 later accepted papers report PartField as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy