AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Multi-view 3D Models from Single Images with a Convolutional Network

Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox

ECCV 2016 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 337 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
use the encoder-decoder network instead of nearest-neighbor HOG baselineunseen view prediction · ShapeNet normal test carscolor error: 0.028 -> 0.013Improved
use the encoder-decoder network instead of nearest-neighbor RGB baselineunseen view prediction · ShapeNet normal test carscolor error: 0.018 -> 0.013Improved
use the network instead of nearest-neighbor HOG+RGB baselineunseen view prediction · ShapeNet difficult test carscolor error: 0.036 -> 0.028Improved
use the network instead of nearest-neighbor RGB baselineunseen view prediction · ShapeNet difficult test carsdepth error: 0.0265 -> 0.0207Improved
use the network instead of nearest-neighbor HOG baselineunseen view prediction · ShapeNet normal test carsdepth error: 0.0058 -> 0.0057No clear effect
use the network instead of Dosovitskiy et al.unseen view prediction · ShapeNet chairs testaverage error: 0.0308 -> 0.0208Improved
render training data realistically (random lights, alpha compositing, smoothing) instead of basic rendering (ablation)multi-view 3D network · real car imagesqualitative shape estimationImproved
add adversarial loss (alpha=0.01) to squared Euclidean loss (ablation)multi-view 3D network · ShapeNet carsimage sharpness and shapeMixed
add data augmentation (ablation)multi-view 3D network · ShapeNet carsgeneralizationNo clear effect
use deeper and wider networks (ablation)multi-view 3D network · ShapeNet carsperformanceNo clear effect

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