Open Source
T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals
arXiv cs.GR0 views
arXiv:2611.06974v1 Announce Type: cross Abstract: Triangle-based splatting connects novel view synthesis with conventional graphics pipelines, but often requires excessive tessellation to preserve appearance details. We present T$^2$-Splat, which decouples topology adaptation from appearance refinement. Safe Restricted Delaunay Triangulation (Safe RDT) initializes mesh connectivity. Dynamic Topology Evolution (DTE) then adapts triangle allocation through edge collapse and vertex split operations. Residual per-face Mip-textures then refine appearance on the fixed mesh using scale-adaptive filtering. Experiments on Mip-NeRF 360, Tanks & Temples, and DTU demonstrate competitive results with compact meshes. T$^2$-Splat improves PSNR by 0.71dB over MeshSplatting on Mip-NeRF 360. Additional compression experiments demonstrate flexible control of mesh complexity, supporting face budgets as low as 10% of the original face count. Project page: https://t2-splat.github.io/.
Source：https://arxiv.org/abs/2611.06974PreviousREACT: Towards Real-Time Completion of Skeletal Motion SignalsNextStructure from Collision via Hypothesis-Space Reasoning
Related posts
Quand HackerTV rencontre la rééducation visuelle : mon parcours de dev amblyope avec Amblyotube sur Meta Quest 3S
0dev.to
When Did a Token Stop Being a Coin? Meet Deduplication 🔍
0HackerNoon
I kept Doom's 1993 engine and wrote a new renderer for it
0dev.to OpenSource
7 multistream chat tools compared, every cell sourced to their own docs
0dev.to OpenSource
Show HN: FuckCaptcha – a field guide to 39 CAPTCHA types and how they break
0Hacker News New
Show HN: Maple – Run Gemma 4 26B on a 6GB Laptop GPU at 45 TPS (Sub-2-BPW)
0Hacker News New