Signals 4 · free daily AI digest

FunArt: Decoding Functional Structure and Articulation from Generative 3D Latents

Paper recorded by Signals 4 on 2026-09-17 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18

Category: cs.CV · 计算机视觉 · first seen 2026-09-18

Abstract

To operate effectively in human environments, robots must identify articulated objects, segment their movable and interactive parts, and estimate their kinematic models. Existing articulated scene representations typically recover kinematics from observed interactions, while methods operating on static scans often decouple articulation from functional interactive elements. We present FunArt, a fra

Read on arXiv →

#6 most recent of 237 cs.CV papers we have recorded · ↑ newer: Towards Scaling Marine Perception with Synthetic Data · ↓ older: Learning Foresight without Explicit Trajectories for 3D Diffusion Poli
Cite this page: FunArt: Decoding Functional Structure and Articulation from Generative 3D Latents: the #6 most recent of 237 cs.CV papers we have recorded (as of 2026-09-17). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/funart-decoding-functional-structure-and-articulation-from-generative-3d-latents.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions