AI Paper Atlas

Research map / 3D vision / Face and shape

PRIF: Primary Ray-Based Implicit Function

Brandon Y. Feng, Yinda Zhang, Danhang Tang, Ruofei Du, Amitabh Varshney

ECCV 2022 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 19 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 reference point f_r instead of Plucker moment vector (ablation)PRIF · ShapeNetCore Car generativemean Chamfer distance: 2.397 -> 1.961Improved
use reference point f_r instead of Plucker moment vector (ablation)PRIF · ShapeNetCore Chair generativemean Chamfer distance: 2.603 -> 0.982Improved
use reference point f_r instead of Plucker moment vector (ablation)PRIF · ShapeNetCore Lamp generativemean Chamfer distance: 4.838 -> 3.276Improved
reparametrize ray with perpendicular foot f_r rather than origin p_r (ablation)PRIF · single shape and novel raysChamfer distanceImproved
remove outliers from predicted hit points (ablation)PRIF · single shapeChamfer distanceNo clear effect
reduce MLP width from 2.96M to 1.35M parameters (ablation)PRIF · ShapeNetCore Car generativemean Chamfer distance: 1.961 -> 2.055Hurt
increase noise level from 0.01 to 0.1 (ablation)PRIF · ShapeNetCore Car denoisingmean Chamfer distance: 1.929 -> 2.842Hurt
use PRIF instead of SDFPRIF · Stanford single shape: Buddhamean Chamfer distance: 6.119 -> 1.443Improved
use PRIF instead of occupancy functionPRIF · ShapeNetCore Lamp generativemean Chamfer distance: 143.377 -> 3.276Improved
use PRIF instead of DeepSDF sphere tracing for renderingPRIF · 512x512 depth renderingtime (s): 1.01070 -> 0.00578Improved
use PRIF instead of SDF for BunnyPRIF · Stanford single shape: Bunnymean Chamfer distance: 1.717 -> 1.169Improved

Later papers that compared with this method

1 later accepted paper reports PRIF as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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