AI Paper Atlas

Research map / 3D vision / Gaussian splatting

T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals

Zhihao Tang, Youjia Zhang, Mingbo Zhao, Wei Yang

NeurIPS 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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

Proposes T^2-Splat, a mesh splatting framework that adaptively adjusts topology and adds texture residuals to improve novel view synthesis on polygonal primitives.

Problem

Naively applying unstructured splatting to triangle/polygonal primitives fails to exploit their topological advantages, causing over-tessellation and degraded high-frequency appearance in novel view synthesis.

Approach

A mesh splatting framework with adaptive topology and texture residuals, so that mesh structure adapts to scene content and high-frequency detail is carried by residual textures rather than extra geometry.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Safe RDT initialization (ablation)MeshSplatting baseline · Mip-NeRF 360 (9 scenes)faces: 5.3M -> 3.0MImproved
add Safe RDT initialization (ablation)baseline · Mip-NeRF 360LPIPS: 0.30 -> 0.31No clear effect
add Dynamic Topology Evolution (edge collapse + vertex split) (ablation)Safe RDT mesh · Mip-NeRF 360PSNR (dB): 24.81 -> 25.12Improved
add DTE on top of 8x8 textures (ablation)Safe RDT + MipTex · Mip-NeRF 360PSNR (dB): 25.31 -> 25.49Improved
add 4x4 residual Mip-textures (ablation)DTE mesh · Mip-NeRF 360PSNR (dB): 25.12 -> 25.43Improved
increase texture resolution from 4x4 to 8x8 (ablation)T2-Splat · Mip-NeRF 360LPIPS: 0.26 -> 0.23Improved
add DTE (cost: training time) (ablation)Safe RDT · Mip-NeRF 360training time (min): 43 -> 57Hurt
reduce face budget to 50% (ablation)T2-Splat · GardenPSNR (dB): 25.68 -> 25.38No clear effect
reduce face budget to 10% (ablation)T2-Splat · GardenPSNR (dB): 25.68 -> 23.93Hurt
T2-Splat vs MeshSplatting on Tanks & TemplesT2-Splat · Tanks & TemplesPSNR (dB): 21.12 vs 20.52Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Experimental setup

Builds on: triangle 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