Research map / Point clouds / Shape and surface completion

Shape as Line Segments: Accurate and Flexible Implicit Surface Representation

ICLR 2025 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a line-segment-based implicit surface representation that encodes shapes via segments instead of closest-distance fields, aiming for accurate and flexible surface extraction.

Problem

Distance field-based implicit representations (signed/unsigned distance fields) rely on closest point distances, causing inaccurate interpolation along cube edges during surface extraction and ill-defined gradients at certain locations that distort reconstructions.

Approach

Represents the surface using line segments rather than closest-distance values, avoiding the interpolation inaccuracies and ill-defined gradients of distance fields.

Experimental setup

Baselines: signed distance fields unsigned distance fields

Builds on: signed distance fields unsigned distance fields

Closest papers by meaning

• LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions (AAAI 2024 · similarity 0.86)
• 3D Neural Edge Reconstruction (CVPR 2024 · similarity 0.86)
• Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.86)
• MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction (NeurIPS 2025 · similarity 0.86)
• DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.86)
• SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision (NeurIPS 2024 · similarity 0.85)