AI Paper Atlas

Research map / 3D vision / 3D generation

Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning

Xinhua Cheng, Yanmin Wu, Mengxi Jia, Qian Wang, Jian Zhang

CVPR 2023 · 3D vision › 3D generation · approach: Semantic scene completion · 6 citations (OpenAlex)

This paper tried a common change: Larger batch size

Train PCFF with a larger batch size · Replica · PSNR: 32.28 -> 32.77 Improved

What 785 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
Train PCFF with network-inferred panoptic labels using instance quadruplet metric learningPCFF · ScanNet target-object extractionIoU: 0.486 -> 0.891Improved
Use semantic-appearance hierarchical learning (SAHL) (ablation)PCFF · ScanNet 0192PSNR: 26.84 -> 26.86Improved
Use semantic-appearance hierarchical learning (SAHL) (ablation)PCFF · Replica office4PSNR: 31.52 -> 31.68Improved
Add semantic-guided regional refinement (SGRR) to SAHL (ablation)PCFF · ScanNet 0192PSNR: 26.86 -> 27.02Improved
Add semantic-guided regional refinement (SGRR) to SAHL (ablation)PCFF · Replica office4PSNR: 31.68 -> 31.86Improved
Add instance quadruplet metric learning (IQML) to SAHL and SGRR (ablation)PCFF · ScanNet 0192PSNR: 27.02 -> 26.96Hurt
Add instance quadruplet metric learning (IQML) to SAHL and SGRR (ablation)PCFF · Replica office4PSNR: 31.86 -> 31.76Hurt
Replace the proposed quadruplet scheme with triplet metric loss (ablation)PCFF · ScanNet 0192PSNR: 26.89 vs. 26.96Hurt
Replace the proposed quadruplet scheme with triplet metric loss (ablation)PCFF · Replica office4PSNR: 31.65 vs. 31.76Hurt
Use the inverse quadruplet margin scheme instead of smaller margins for hard negatives (ablation)PCFF · ScanNet 0192PSNR: 26.88 vs. 26.96Hurt
Use the inverse quadruplet margin scheme instead of smaller margins for hard negatives (ablation)PCFF · Replica office4PSNR: 31.67 vs. 31.76Hurt
Train PCFF with a larger batch sizePCFF · ReplicaPSNR: 32.28 -> 32.77Improved

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