AI Paper Atlas

Research map / 3D vision / 3D generation

Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars

Chenfanfu Jiang, Siyuan Qi, Yixin Zhu, Siyuan Huang, Jenny Lin, Lap-Fai Yu, Demetri Terzopoulos, Song Chun Zhu

IJCV 2018 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 82 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
pretrain on synthetic data before fine-tuning on NYUv2FCN of [146] · NYU-Depth V2 normal estimationmean angular error: 21.74 -> 21.47Improved
pretrain on synthetic data before fine-tuning on NYUv2FCN of [146] · NYU-Depth V2 normal estimationaccuracy within 11.25 degrees: 39.37 -> 39.84Improved
pretrain on synthetic data then fine-tune on NYUv2 instead of training only on NYUv2network of [71] · NYU-Depth V2 depth estimationAbs Rel: 0.233 -> 0.226Improved
train on synthetic data only instead of NYUv2 onlynetwork of [71] · NYU-Depth V2 depth estimationAbs Rel: 0.233 -> 0.241Hurt
train on synthetic data only instead of NYUv2 onlynetwork of [71] · NYU-Depth V2 depth estimationaccuracy delta<1.25: 0.605 -> 0.612Improved
lower noise-level threshold to higher (0.1 instead of 0.001) (ablation)Mantra renderer · Rendering time vs qualityrender time (seconds): 203 -> 30Improved
reduce baseline pixel samples from 3x3 to 1x1 (ablation)Mantra renderer · Rendering time vs qualityrender time (seconds): 203 -> 45Improved
reduce max additional rays from 22 to 3 (ablation)Mantra renderer · Rendering time vs qualityrender time (seconds): 203 -> 36Improved
change illumination intensity of test scenesdepth method [29] · Synthetic benchmark depth estimationAbs Rel: 0.373 -> 0.483Hurt
change illumination color of test scenesdepth method [71] · Synthetic benchmark depth estimationAbs Rel: 0.225 -> 0.332Hurt
change object material properties of test scenesdepth method [71] · Synthetic benchmark depth estimationAbs Rel: 0.225 -> 0.192No clear effect
change illumination color of test scenesnormal method [28] · Synthetic benchmark normal estimationmean angular error: 22.74 -> 26.53Mixed

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