AI Paper Atlas

Research map / 3D vision / 3D generation

Monocular Dense 3D Reconstruction of a Complex Dynamic Scene From Two Perspective Frames

Suryansh Kumar, Yuchao Dai, Hongdong Li

ICCV 2017 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 68 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 two-frame SuperPixelSoup instead of two-frame DMDESuperPixelSoup · MPI SintelMRE: 0.297 -> 0.1669Improved
use SuperPixelSoup instead of best multi-frame baseline BMMSuperPixelSoup · MPI SintelMRE: 0.3121 -> 0.1669Improved
use SuperPixelSoup instead of Depth TransferSuperPixelSoup · Virtual KITTIMRE: 0.2630 -> 0.1045Improved
use SuperPixelSoup instead of DMDESuperPixelSoup · KITTIMRE: 0.148 -> 0.1268Improved
use two-frame SuperPixelSoup instead of multi-frame BMMSuperPixelSoup · Kinect paperMRE: 0.0322 -> 0.0476Hurt
use two-frame SuperPixelSoup instead of multi-frame PTASuperPixelSoup · Kinect tshirtMRE: 0.0420 -> 0.0480Hurt
increase K of the K-NN graph in the ARAP term to 20 (ablation)SuperPixelSoup · MPI Sintelqualitative reconstructionMixed

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