AI Paper Atlas

Research map / 3D vision / 3D generation

Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis

Qi Sun, Hang Zhou, Wengang Zhou, Li Li, Houqiang Li

ECCV 2024 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 21 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 tree-guided BFS ordering instead of single random ordering (ablation)Forest2Seq · 3D-FRONT living roomFID: 49.4 -> 36.1Improved
use scene forest instead of single scene tree (ablation)Forest2Seq · 3D-FRONT living roomKL: 7.90 -> 5.90Improved
use BFS instead of DFS traversal of the forest (ablation)Forest2Seq · 3D-FRONT living roomFID: 40.5 -> 35.2Improved
use multiple random orderings instead of a single random ordering (ablation)autoregressive scene model · 3D-FRONT living roomFID: 49.4 -> 43.3Improved
add absolute positional encoding (ablation)Forest2Seq · 3D-FRONT living roomKL: 11.1 -> 5.9Improved
absolute versus relative positional encoding (ablation)Forest2Seq · 3D-FRONT living roomKL: 6.2 vs 5.9No clear effect
add denoising with 0.05 mask/noise rate (ablation)Forest2Seq · 3D-FRONT living roomKL: 6.4 -> 5.9Improved
raise mask/noise rate to 0.2 (ablation)Forest2Seq · 3D-FRONT living roomKL: 5.9 -> 12.2Hurt
use MEDC (add GIoU term) instead of plain Euclidean clustering (ablation)scene tree parsing · 3D-FRONT scene parsingAHD: 0.53 -> 0.84Improved

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