# DeepSurfels: Learning Online Appearance Fusion

arXiv: https://arxiv.org/abs/2012.14240 · HTML: https://mlsanity.com/paper/2012.14240/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2020.

## Built on by (most cited first, 13 of 13)

- [Shape As Points: A Differentiable Poisson Solver](https://mlsanity.com/paper/2106.03452/) (2021)
- [Point-SLAM: Dense Neural Point Cloud-based SLAM](https://mlsanity.com/paper/2304.04278/) (2023)
- [Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting](https://mlsanity.com/paper/2312.10070/) (2023)
- [LEAP: Learning Articulated Occupancy of People](https://mlsanity.com/paper/2104.06849/) (2021)
- [GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization](https://mlsanity.com/paper/2312.05133/) (2023)
- [MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images](https://mlsanity.com/paper/2106.11944/) (2021)
- [KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints](https://mlsanity.com/paper/2205.04992/) (2022)
- [SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes](https://mlsanity.com/paper/2304.08971/) (2023)
- [GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling](https://mlsanity.com/paper/2409.12954/) (2024)
- [SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs](https://mlsanity.com/paper/2404.00469/) (2024)
- [Multi-sensor large-scale dataset for multi-view 3D reconstruction](https://mlsanity.com/paper/2203.06111/) (2022)
- [HashPoint: Accelerated Point Searching and Sampling for Neural Rendering](https://mlsanity.com/paper/2404.14044/) (2024)
- [Advances and Trends in the 3D Reconstruction of the Shape and Motion of Animals](https://mlsanity.com/paper/2508.16062/) (2025)

## Abstract (arXiv)

We present DeepSurfels, a novel hybrid scene representation for geometry and appearance information. DeepSurfels combines explicit and neural building blocks to jointly encode geometry and appearance information. In contrast to established representations, DeepSurfels better represents high-frequency textures, is well-suited for online updates of appearance information, and can be easily combined with machine learning methods. We further present an end-to-end trainable online appearance fusion pipeline that fuses information from RGB images into the proposed scene representation and is trained using self-supervision imposed by the reprojection error with respect to the input images. Our method compares favorably to classical texture mapping approaches as well as recent learning-based techniques. Moreover, we demonstrate lower runtime, im-proved generalization capabilities, and better scalability to larger scenes compared to existing methods.