AI Paper Atlas

Research map / 3D vision / Face and shape

3D VR Sketch Guided 3D Shape Prototyping and Exploration

Ling Luo, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song, Yulia Gryaditskaya

ICCV 2023 · 3D vision › Face and shape · approach: 3D shape generative modeling · 24 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
train encoder jointly on sketches and shapes instead of sketches only or shapes only (ablation)sketch-to-shape auto-encoder · VR chair sketches (ShapeNet, test 202)F_shape(G^{e^c}): 0.834 -> 0.357 (vs Shape AE); 0.437 -> 0.357 (vs Sketch AE L_SDF)Improved
add L_SDF to L_L1 losses (ablation)joint auto-encoder · VR chair sketches (ShapeNet, test 202)F_shape(G^{e^g}): 0.199 -> 0.140Improved
add NCE contrastive losses (ablation)joint auto-encoder · ShapeNet chair shapes (shape input)F_shape(G^{e^g}): 0.140 -> 0.126Improved
add sketch fidelity loss L_sketch to the encoder losses (ablation)joint auto-encoder · VR chair sketches (ShapeNet, test 202)F_shape(G^{e^c}): 0.373 -> 0.357Improved
train CNF on inverted auto-decoder codes d^g instead of encoder codes e^g (ablation)CNF · VR chair sketches, CNF generationdiversity D_gnrtns: 0.043 -> 0.165Improved
train CNF on inverted codes d^g instead of e^g (ablation)CNF · VR chair sketches, CNF generationshape fidelity to reference F_shape^avg: 0.380 -> 0.420Hurt
add sketch consistency loss L_sketch,CNF to CNF training (K=1) (ablation)CNF(d^g) · VR chair sketches, CNF generationsketch fidelity F_sketch^avg: 0.030 -> 0.019Improved
increase K samples in L_sketch,CNF from 1 to 8 (ablation)CNF(d^g) + L_sketch,CNF · VR chair sketches, CNF generationsketch fidelity F_sketch^avg: 0.019 -> 0.017Improved
K=4 instead of K=1 in L_sketch,CNF (ablation)CNF(d^g) + L_sketch,CNF · VR chair sketches, CNF generationF_shape(G^{e^c}): 0.366 -> 0.397Hurt
use 3D VR sketches instead of 2D sketches as inputsketch encoder with L_align and L_SDF · VR chair sketches (ShapeNet, test 202)F_shape: 0.833 -> 0.437Improved
use clean curve networks instead of freehand sketches as inputCNF generation · ModelNet chairs (139)F_shape(G^{e^c}) and diversity: 0.366 -> 0.237 (shape fidelity); diversity 0.161 -> 0.142Improved
generate with CNF instead of retrieving top-5 shapessketch-to-shape pipeline · VR chair sketches, retrieval comparisonF_shape^avg: 1.132 vs 0.431Improved

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