AI Paper Atlas

Research map / 3D vision / Face and shape

Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images Using a View-Based Representation

Sai Rajeswar, Fahim Mannan, Florian Golemo, Jérôme Parent-Lévesque, David Vázquez, Derek Nowrouzezahrai, Aaron C. Courville

IJCV 2020 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 10 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 reconstruction loss to adversarial loss (ablation)Pix2Shape · ShapeNet scenes reconstruction, 0 degreesChamfer distance: 1.927 -> 0.1120Improved
add adversarial loss to reconstruction loss (ablation)Pix2Shape · ShapeNet scenes reconstruction, 80 degreesChamfer distance: 0.1925 -> 0.1433Improved
add adversarial loss to reconstruction loss (ablation)Pix2Shape · ShapeNet scenes reconstruction, 0 degreesChamfer distance: 0.1066 -> 0.1120Hurt
add mutual information loss (ablation)Pix2Shape · 3D-IQTT (1000 labels)accuracy: 0.4921 -> 0.7020Improved
add mutual information loss (ablation)Pix2Shape · 3D-IQTT (0 labels)accuracy: 0.4224 -> 0.5526Improved
add adversarial loss to reconstruction plus mutual info (ablation)Pix2Shape · 3D-IQTT (1000 labels)accuracy: 0.6272 -> 0.7020Improved
add reconstruction loss to adversarial loss (ablation)Pix2Shape · 3D-IQTT (1000 labels)accuracy: 0.4454 -> 0.4921Improved
use Pix2Shape instead of Perspective Transformer NetsPTN · Shape scenes reconstructionChamfer distance: 0.145 -> 0.103Improved
use Pix2Shape instead of PTNPTN · ShapeNet scenes reconstructionMSE-depth: 0.103 -> 0.053Improved
use Pix2Shape instead of Rezende et al.Rezende et al. · 3D-IQTT (0 labels)accuracy: 0.5202 -> 0.5519Improved
use Pix2Shape instead of Rezende et al.Rezende et al. · 3D-IQTT (1,000 labels)accuracy: 0.7001 -> 0.7012No clear effect
add labeled samples (0 to 1,000)Pix2Shape · 3D-IQTTaccuracy: 0.5519 -> 0.7012Improved

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