AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views

Wesley Khademi, Fuxin Li

NeurIPS 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views

Read the paperCheck your idea against 137,217 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 method for sparse-view scene completion that jointly completes geometry and appearance for 3D Gaussian Splatting-based novel view synthesis, rather than relying on 2D inpainting diffusion models alone.

Problem

3D Gaussian Splatting degrades under sparse views because it cannot extrapolate beyond observed regions, so occluded and sparsely observed areas need to be inpainted and completed.

Approach

Unlike prior approaches that complete scenes with 2D inpainting diffusion models or geometry-only completion, the paper performs joint geometry and appearance scene completion from sparse views (abstract is truncated, so details are not confirmed).

Experimental setup

Baselines: 3D Gaussian Splatting

Builds on: 3D Gaussian Splatting

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy