AI Paper Atlas

Research map / 3D vision / 3D generation

GNeSF: Generalizable Neural Semantic Fields

Hanlin Chen, Chen Li, Mengqi Guo, Zhiwen Yan, Gim Hee Lee

NeurIPS 2023 · 3D vision › 3D generation · approach: Semantic scene completion · 4 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
Use soft voting of 2D semantic observations instead of a direct semantic headGNeSF · ScanNet val, novel scenemIoU: 39.1 -> 71.6Improved
Use GNeSF instead of Semantic-RayScanNet val, novel scene · ScanNet val, novel scenemIoU: 56.0 -> 71.6Improved
Use GNeSF instead of Mask2Former with rendered imagesScanNet val, novel scene · ScanNet val, novel scenemIoU: 64.6 -> 71.6Improved
Use GNeSF instead of Semantic-NeRFScanNet val, novel view · ScanNet val, novel viewmIoU: 96.8 -> 93.3Hurt
Use GNeSF instead of NeuralReconScanNet test 3D semantic segmentation · ScanNet test, 3D semantic segmentationmIoU: 51.5 -> 55.1Improved
Apply the ScanNet-trained GNeSF model to ReplicaGNeSF · Replica, 3D semantic segmentation3D mIoU: 26.2 -> 43.8Improved
Use mesh geometry (ablation)GNeSF · ScanNet val, 3D semantic segmentationmIoU: 58.8 -> 60.4Improved
Add semantic voting instead of direct point-semantic prediction (ablation)GNeSF · ScanNet 3D semantic segmentationmIoU: 37.5 (+0) -> 57.3 (+19.8)Improved
Represent semantics as probabilities rather than logits (ablation)GNeSF soft voting · ScanNet 3D semantic segmentationmIoU: 57.3 -> 57.9 (+0.6)Improved
Add the visibility module to filter occluded views (ablation)GNeSF probability voting · ScanNet 3D semantic segmentationmIoU: 57.9 -> 58.8 (+0.9)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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