AI Paper Atlas

Research map / 3D vision / Face and shape

S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces

Haoyu Wu, Alexandros Graikos, Dimitris Samaras

ICCV 2023 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 23 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 MVS probability volumes with soft consistency only, without extra optimization (ablation)S-VolSDF on CasMVSNet · DTU 3-viewChamfer distance (mm): 1.920 -> 1.711Improved
add generalized cross entropy (noise-tolerant) weight loss instead of cross entropy (ablation)S-VolSDF · DTU 3-viewChamfer distance (mm): 1.534 -> 1.320Improved
use weight loss instead of MSE to filtered MVS depth (ablation)S-VolSDF · DTU 3-viewChamfer distance (mm): 1.792 -> 1.320Improved
use probability volumes instead of argmax depth maps as MVS input (ablation)S-VolSDF · DTU 3-viewChamfer distance (mm): 1.543 -> 1.320Improved
plug S-VolSDF into different MVS models (ablation)TransMVSNet, UCSNet, CasMVSNet · DTU 3-viewChamfer distance (mm): 2.92 -> 1.80; 2.20 -> 1.52; 1.92 -> 1.32Improved
add image interpolation to the rendering process (Ours_IR) (ablation)S-VolSDF · DTU novel view synthesisLPIPS: 0.321 -> 0.157Improved
apply the method to MVS stages 1, 1+2, 1+2+3 instead of stage 1 only (ablation)S-VolSDF CasMVSNet · DTU 3-viewChamfer distance (mm): 1.320 -> 1.312 -> 1.309No clear effect
vary loss parameter q across 0.2 to 0.8 (ablation)weight loss · DTU 3-viewChamfer distance (mm): overall error 1.32-1.44No clear effect
increase input views from 3 to 9 (ablation)S-VolSDF versus VolSDF · DTU novel view synthesis PSNRPSNR: 3 views 20.21 vs 16.99; 9 views 22.98 vs 23.04Mixed
optimize with S-VolSDF versus fully trained VolSDFS-VolSDF · DTU training timeoptimization time: 10-15 minutes versus 4-10 hoursImproved
lower the image resolution for three given views (ablation)S-VolSDF versus CasMVSNet and VolSDF · DTUChamfer distance (mm): 1.32, 1.33, 1.33 across low, mid, highNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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