AI Paper Atlas

Research map / 3D vision / 3D generation

Neural Wireframe Renderer: Learning Wireframe to Image Translations

Yuan Xue, Zihan Zhou, Xiaolei Huang

ECCV 2020 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 5 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 joint representation learning (wireframe decoder branch) (ablation)Ours · Wireframe dataset indoor test (422 images)FID: 97.49 -> 70.73Improved
add joint representation learning (wireframe decoder branch) (ablation)Ours · Wireframe dataset indoor test (422 images)LPIPS: 2.85 -> 2.77Improved
add joint representation learning (wireframe decoder branch) (ablation)Ours · Wireframe dataset indoor test (422 images)SSIM: 0.092 -> 0.102Improved
add joint representation learning (wireframe decoder branch) (ablation)Ours · Wireframe dataset indoor test (422 images)sAP5: 26.7 -> 60.1Improved
add joint representation learning (wireframe decoder branch) (ablation)Ours · Wireframe dataset indoor test (422 images)sAP10: 34.4 -> 64.1Improved
add joint representation learning (wireframe decoder branch) (ablation)Ours · Wireframe dataset indoor test (422 images)sAP15: 37.5 -> 65.7Improved
use multi-scale discriminators and adversarial perceptual loss (pix2pixHD over pix2pix)pix2pix · Wireframe dataset indoor test (422 images)FID: 186.91 -> 153.36Improved
use pretrained-VGG perceptual loss without joint representation instead of pix2pixHD's learned perceptual losspix2pixHD · Wireframe dataset indoor test (422 images)FID: 153.36 -> 97.49Improved
use full model instead of SPADESPADE · Wireframe dataset indoor test (422 images)FID: 93.90 -> 70.73Improved
use full model instead of SPADESPADE · Wireframe dataset indoor test (422 images)sAP5: 54.7 -> 60.1Improved
use full model instead of pix2pixHD in human preferencepix2pixHD · Human preference study (422 test images)preference rate (%): 3.7% -> 65.1%Improved
add joint wireframe/image generation to StackGANv2StackGANv2 · Noise-to-image generation (wireframe dataset)Inception score: 2.92 -> 3.08Improved

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