AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images

Matthew Purri, Kristin Dana

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling · 22 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
make the regression network cross-modal (ablation)Single image · SPS single imageavg R2 / %err: 0.34/39.1 -> 0.46/34.3Improved
add conditional GAN adversarial objective to cross-modal network (ablation)Single image · SPS single imageavg R2: 0.46 -> 0.49Improved
add conditional GAN adversarial objective to cross-modal network (ablation)Single image · SPS single imageavg %err: 34.3 -> 36.2Hurt
add material class auxiliary classification (ablation)Cross-modal · SPS single imageavg R2: 0.46 -> 0.45Hurt
add tactile cluster auxiliary classification (ablation)Cross-modal · SPS single imageavg R2: 0.46 -> 0.48Improved
add visuo-tactile cluster auxiliary classification (ablation)Cross-modal · SPS single imageavg R2: 0.46 -> 0.49Improved
add adversarial objective on top of visuo-tactile classification (ablation)Cross-modal + visuo-tactile · SPS single imageavg R2: 0.49 -> 0.50Improved
use all available images (Late Fusion) instead of a single imageSingle image · SPS multi-imageavg R2: 0.50 -> 0.11Hurt
use equidistant sampling of views instead of single imageSingle image · SPS multi-imageavg R2: 0.50 -> 0.51Improved
use random view sampling instead of single imageSingle image · SPS multi-imageavg R2: 0.50 -> 0.47Hurt
use learned viewpoint selection (NVS) instead of equidistant samplingEquidistant · SPS multi-imageavg R2: 0.51 -> 0.53Improved
use variational-bottleneck viewpoint selection (VB-NVS) instead of NVSNVS · SPS multi-imageavg R2: 0.53 -> 0.55Improved

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