AI Paper Atlas

Research map / 3D vision / Depth and stereo

Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance

Hang Zhang, Kristin Dana, Ko Nishino

ECCV 2016 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 25 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 DRC-opt hashing instead of directly hashing CNN activations (CNN-ITQ)hash codes · Reflectance disksrecognition precision (%): 51.9 -> 60.2Improved
use DRC-opt instead of FV-SIFT-Hashhash codes · Reflectance disksrecognition precision (%): 64.5 -> 60.2Hurt
use DRC-opt instead of FV-SIFT-Hashhash codes · FMDrecognition precision (%): 48.3 -> 65.5Improved
use DRC-opt instead of FV-SIFT-Hashhash codes · DTDrecognition precision (%): 43.6 -> 55.8Improved
use DRC-opt instead of FV-SIFT-Hashhash codes · KTHrecognition precision (%): 72.0 -> 77.2Improved
use optimized DRC-opt instead of random DRC (ablation)DRC · DTDrecognition precision (%): 55.4 -> 55.8Improved
use optimized DRC-opt instead of random DRC (ablation)DRC · Reflectance disksrecognition precision (%): 59.9 -> 60.2No clear effect
use DRC retrieval instead of neural net regression for frictionDRC · Reflectance-frictionmean percentage error (%): 14.74 -> 11.15Improved
use FV pooling of CNN activations instead of VLAD (ablation)KBE hashing · KTHrecognition precision (%): 75.6 -> 74.4No clear effect

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