AI Paper Atlas

Research map / 3D vision / Gaussian splatting

N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields

Yash Bhalgat, Iro Laina, Joao F Henriques, Andrew Zisserman, Andrea Vedaldi

ECCV 2024 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 29 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 composite embedding instead of explicit scale selection (ablation)N2F2 · expanded LERF (4 scenes)mIoU: 53.7 -> 54.4Improved
use composite embedding instead of explicit scale selection (ablation)N2F2 · expanded LERF (4 scenes)localization accuracy: 87.0 -> 87.9Improved
use all dimensions for scale supervision (k=1 vs k=170) (ablation)N2F2 · LERF teatimemIoU: 66.4 -> 69.2Improved
use composite embedding to compute one relevancy map per queryN2F2 · querying timespeed: 1.7x faster than LangSplat, 26x faster than LERFImproved
use a weaker segmenter (Detic instead of SAM) (ablation)N2F2 · LERF teatimemIoU: 69.2 -> 66.2Hurt
remove nested feature design (ablation)N2F2 · LERFmIoU: -2.0 mIoU, -2.5% localization when removedImproved
use pure-MLP backbone instead of TriPlane+MLP (ablation)N2F2 · LERFconvergence speed: 2.3x more memory-efficient but 20x slower convergenceMixed
use N2F2 instead of LangSplat on simple 3D-OVS scenesN2F2 · 3D-OVSmIoU: 93.4 -> 93.9No clear effect
use N2F2 on compound queries instead of LangSplatN2F2 · expanded LERF ramen compound queriesmIoU: 35.1 -> 42.3Improved

Later papers that compared with this method

2 later accepted papers report N2F2 as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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