Introduction

This repository is my personal research notebook.
It serves as a collection of surface-reconstruction–related papers that I come across anytime and anywhere.

Paper lists

This repo. just roughly records the contributions of each paper (Why->What->How). My notes are mainly recorded on Notion.

Extensive Reading

Intensive Reading

• NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance. Hanlin Chen et.al. ArXiv, 2023. [Paper] [No Code] (★★☆☆☆)

  • Scale regularization (the basis of follow-up 3d Gaussian planes).
  • Surface normal alignment of NeuS.

• SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering. Antoine Guédon, Vincent Lepetit. CVPR, 2024. [Paper] [Code] (★★☆☆☆)(No reading code)

  • To reduce interference from overlapping Gaussians, the Gaussian nearest to the point $p$ is selected.
    The SDF is then defined by shortening the distance along its smallest scale axis, and this estimated SDF is regularized toward the ground-truth SDF to achieve surface alignment.

• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields. Binbin Huang et.al. SIGGRAPH, 2024. [Paper] [Code] (★★★★☆)

  • Initialize 2D Gaussian primitives to ensure multi-view consistency, and use homogeneous transformations to remove the errors introduced by affine projection approximations.

• High-quality Surface Reconstruction using Gaussian Surfels. Pinxuan Dai, Jiamin Xu et.al. SIGGRAPH, 2024. [Paper] [Code] (★★★★☆)

  • Introduces Gaussian surfels (with scale.z = 0) and adaptively adjusts pixel-wise depths when the surfels align with slanted surfaces.

• Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes. Zehao Yu et.al. TOG, 2024. [Paper] [Code] (★★★☆☆)

• RaDe-GS: Rasterizing Depth in Gaussian Splatting. Baowen Zhang et.al. ArXiv, 2024. [Paper] [Code] (Unread)

• PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction. Danpeng Chen et.al. TVCG, 2024 [Paper] [Code] (★★★☆☆)

• GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction. Zuoliang Zhu et.al. ACM TOG, 2025. [Paper] [Code]

• GS-2M: Gaussian Splatting for Joint Mesh Reconstruction and Material Decomposition. D. M. Nguyen et.al. ArXiv, 2025. [Paper] [Code] [Note] (Unread)

• VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction. Hanlin Chen et.al. NIPS, 2024. [Paper] [Code]

Extension (Preparing)

• GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes. Gaochao Song, Chong Cheng et.al. NeurIPS, 2025. [Paper] [Code] [Note]

• GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction. Jiepeng Wang et.al. ArXiv, 2024. [Paper] [Code] (Unread)

• αSurf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity. Keyang Ye et.al. 3DV, 2025. [Paper] [Code] (Unread)

• Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes. Stefano Esposito et.al. CVPR, 2025. [Paper] [Code] (Unread)

• When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering. Keyang Ye et.al. TOG, 2025. [Paper] [No Code] (Unread)

• Quadratic Gaussian Splatting: High Quality Surface Reconstruction with Second-order Geometric Primitives. Ziyu Zhang, Binbin Huang et.al. ICCV, 2025. [Paper] [Code] (★★★★☆)

• MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions. Qingyuan Zhou et.al. ICCV, 2025. [Paper] [Code] (Unread)

• MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction. Antoine Guédon, Diego Gomez et.al. TOG, 2025. [Paper] [Code] (Unread)

reference

• High-Quality Surface Splatting on Today's GPUs. gaussian filter in 2dgs
  • anti-aliasing in magnified as well as in minified regions