Research map / 3D vision / Gaussian splatting
3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields
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 combining 3D Gaussian Splatting with a self-learned neural view-dependent color field to model smoother radiance fields and reduce floaters.
Problem
Discrete 3D Gaussians in 3DGS produce poor depth, few geometry details, and many floaters, making smooth radiance field modeling difficult for novel view synthesis.
Approach
Learns a neural view-dependent color field alongside the explicit Gaussians (self-learned, per the title) so that color is smoothly modeled rather than stored only as per-Gaussian attributes; based on the title and truncated abstract only.
Experimental setup
Builds on: 3D Gaussian Splatting
Closest papers by meaning
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.93)
- Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields (CVPR 2024 · similarity 0.91)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.91)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.91)
- Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS (NeurIPS 2025 · similarity 0.91)
- RNG: Relightable Neural Gaussians (CVPR 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.