AI Paper Atlas

Research map / 3D vision / Face and shape

TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches

Langzhe Gu, Hung-Jui Huang, Mohamad Qadri, Michael Kaess, Wenzhen Yuan

ECCV 2026 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 0 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
add class-level text prompt instead of incorrect prompt (an airplane) (ablation)TouchAnything · Real objects, 20 touches (4 objects)EMD: bottle 0.0105 -> 0.0057; camera 0.0180 -> 0.0098Improved
use class-level prompt instead of empty prompt (ablation)TouchAnything · Real objects, 20 touches (4 objects)EMD: potted meat can 0.0086 -> 0.0062; tomato soup can 0.0089 -> 0.0077Improved
use detailed instance-specific prompt instead of class-level prompt (ablation)TouchAnything · Real objects, 20 touchesEMD: bottle 0.0057 -> 0.0089; camera 0.0098 -> 0.0097No clear effect
use all available touches instead of 20 or 40 (ablation)TouchAnything · Real objectsEMD: bottle p3 0.0057 -> 0.0066 (all)No clear effect
add diffusion prior (SDS) to tactile-only reconstruction (ablation)TouchAnything · Real objectsreconstruction quality (qualitative)Improved
add stage 2 DMTet refinement at 512x512 rendering (ablation)TouchAnything · Real objectssurface detail (qualitative)Improved
replace trained tactile priors with pretrained 2D diffusion guidanceTouchAnything vs TouchSDF · ShapeNet Guitar (20 touches)EMD: 0.155 -> 0.060Improved
replace Touch2Shape with TouchAnythingTouchAnything vs Touch2Shape · ShapeNet Camera (20 touches)EMD: 0.056 -> 0.047Improved
replace Touch2Shape with TouchAnythingTouchAnything vs Touch2Shape · ShapeNet Jar (20 touches)EMD: 0.055 -> 0.053Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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