AI Paper Atlas

Research map / 3D vision / Depth and stereo

Image Based Reconstruction of Liquids From 2D Surface Detections

Florian Richter, Ryan K. Orosco, Michael C. Yip

CVPR 2022 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 7 citations (OpenAlex)

Check 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
Add density and collision constraints to image-loss optimization (ablation)Liquid particle reconstruction · Endoscopic Liquid3D reconstruction qualityImproved
Add particle prediction from the previous time step (ablation)Liquid particle reconstruction · Endoscopic Liquid3D reconstruction qualityImproved
Use density and collision constraints with dynamic predictionLiquid particle reconstruction · Simulated FountainIoU3DImproved
Replace the density constraint with Schenck & Fox constraints (ablation)Liquid particle reconstruction · Pouring Milk3D reconstruction qualityHurt
Replace Pulsar with DSS for rendering gradients (ablation)Liquid particle reconstruction · Pouring Milk3D reconstruction qualityHurt
Use uniform random selection rather than selecting particles to best satisfy density (ablation)Particle insertion and removal · Pouring Milk3D reconstruction qualityHurt
Add a density constraint (ablation)Liquid particle reconstruction · Pouring Milk3D reconstruction qualityImproved
Add a collision constraint (ablation)Liquid particle reconstruction · Endoscopic Liquid3D reconstruction qualityImproved

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