AI Paper Atlas

Research map / 3D vision / Face and shape

Octree Generating Networks: Efficient Convolutional Architectures for High-Resolution 3D Outputs

Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox

ICCV 2017 · 3D vision › Face and shape · approach: 3D shape generative modeling · 761 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 known octree structure at test time (Prop-known) instead of predicted (ablation)OGN autoencoder · ShapeNet-cars autoencoder 64^3IoU: 0.884 -> 0.904Improved
fine-tune with Prop-pred after Prop-known training (ablation)OGN autoencoder 2^3 filters · ShapeNet-cars autoencoder 64^3IoU: 0.862 -> 0.884Improved
fine-tune with Prop-pred after Prop-known training (ablation)OGN autoencoder 4^3 filters · ShapeNet-cars autoencoder 64^3IoU: 0.804 -> 0.885Improved
use 4x4 up-convolutions instead of 2x2 (ablation)OGN autoencoder · ShapeNet-cars autoencoder 64^3IoU: 0.884 -> 0.885No clear effect
interleave 3x3 convolutions (IntConv) (ablation)OGN autoencoder · ShapeNet-cars autoencoder 64^3IoU: 0.884 -> 0.885No clear effect
replace dense decoder with OGN (memory)decoder at 512^3 · Decoder efficiencymemory (GB): 74.28 -> 0.88Improved
replace dense decoder with OGN (time)decoder at 256^3 · Decoder efficiencyiteration time (s): 3.89 -> 0.64Improved
replace dense decoder with OGN decodersingle-view reconstruction · ShapeNet-all 32^3mean IoU: 0.590 -> 0.596No clear effect
increase output resolution 64^3 to 128^3 (ablation)OGN shape from ID · ShapeNet-carsIoU: 0.856 -> 0.901Improved
increase output resolution 128^3 to 256^3 (ablation)OGN shape from ID · ShapeNet-cars (full)IoU: 0.901 -> 0.865Hurt
increase output resolution 128^3 to 256^3 on reduced dataset (ablation)OGN shape from ID · ShapeNet-cars (500 models)IoU: 0.922 -> 0.931Improved
increase output resolution 64^3 to 512^3 (ablation)OGN shape from ID · BlendSwapIoU: 0.535 -> 0.969Improved

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