AI Paper Atlas

Research map / 3D vision / 3D generation

SceneDreamer: Unbounded 3D Scene Generation From 2D Image Collections

Zhaoxi Chen, Guangcong Wang, Ziwei Liu

TPAMI 2023 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 73 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 BEV scene encoder (ablation)SceneDreamer · scene generationFID: 80.62 -> 76.73Improved
add BEV scene encoder (ablation)SceneDreamer · scene generationcamera error (CE): 0.044 -> 0.021Improved
add semantic field to BEV input (ablation)SceneDreamer · scene generationFID: 83.20 -> 76.73Improved
add height field to BEV input (ablation)SceneDreamer · scene generationFID: 79.80 -> 76.73Improved
add semantic field to BEV input (ablation)SceneDreamer · scene generationdepth error: 0.401 -> 0.277Improved
use BEV instead of semantic voxels (ablation)SceneDreamer · memory budget 40GBmax supported LOD: 512x512x256 -> 2048x2048x256Improved
use generative hash grid instead of pure MLP (ablation)SceneDreamer · scene generationFID: 88.76 -> 76.73Improved
use generative hash grid instead of MLP with positional encoding (ablation)SceneDreamer · scene generationFID: 83.14 -> 76.73Improved
use generative hash grid instead of HyperNet (ablation)SceneDreamer · scene generationFID: 117.64 -> 76.73Improved
use generative hash grid instead of tri-plane (ablation)SceneDreamer · scene generationFID: 103.86 -> 76.73Improved
add rejection sampling of cameras instead of random sampling (ablation)SceneDreamer · scene generationFID: 102.60 -> 76.73Improved
add rejection sampling instead of area sampling (ablation)SceneDreamer · scene generationFID: 96.90 -> 76.73Improved

Later papers that compared with this method

2 later accepted papers report SceneDreamer as a baseline in their results tables; 2 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