Signals 4 · free daily AI digest

Superquadric Primitive Decomposition of 3D point clouds via Geometric-Aware Inlier Refinement

Paper recorded by Signals 4 on 2026-09-28 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-28 on arXiv · recorded by Signals 4 on 2026-09-29

Category: cs.CV · 计算机视觉 · first seen 2026-09-29

Abstract

The decomposition of 3D point clouds into interpretable geometric primitives remains a longstanding challenge in Computer Vision and Computer Graphics. Among the available representations, superquadrics offer a compact and expressive model capable of capturing a wide range of shapes. However, their estimation is inherently challenging, as it requires solving a non-linear optimization problem and i

Read on arXiv →

#6 most recent of 342 cs.CV papers we have recorded · ↑ newer: Impact of Patient Orientation in Single- and Multi-View Camera Environ · ↓ older: Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vis
Cite this page: Superquadric Primitive Decomposition of 3D point clouds via Geometric-Aware Inlier Refinement: the #6 most recent of 342 cs.CV papers we have recorded (as of 2026-09-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/superquadric-primitive-decomposition-of-3d-point-clouds-via-geometric-aware-inli.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