AI Paper Atlas

Research map / 3D vision / Gaussian splatting

UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras

Yipeng Zhu, Huajian Huang, Tristan Braud, Sai Kit Yeung

ECCV 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add HEALPix-SSIM loss (ablation)UniTriSplat · OmniBlenderPSNR (dB): 26.42 -> 32.57Improved
add radian-space density control (ablation)UniTriSplat · OmniBlenderPSNR (dB): 24.83 -> 32.57Improved
add multi-view consistent final pruning (ablation)UniTriSplat · OmniBlenderPSNR (dB): 32.57 -> 28.27Hurt
use NESTED quadtree search (x4) instead of RING scan (x4) (ablation)UniTriSplat · OmniBlenderPSNR (dB): 32.57 -> 33.64; time 28.2 -> 49.1Mixed
reduce quadtree search depth from x4 to x2 (ablation)UniTriSplat · OmniBlenderPSNR (dB): 33.64 -> 26.49Hurt
reduce quadtree search depth from x4 to x1 (ablation)UniTriSplat · OmniBlenderPSNR (dB): 33.64 -> 20.36Hurt
use higher HEALPix level Ours(H) instead of Ours(L)UniTriSplat · 360Roam 6080x3040PSNR (dB): 21.82 -> 22.53Improved
use lower HEALPix level Ours(L) at low resolutionUniTriSplat · 360Roam 1520x760PSNR (dB): 26.10 -> 23.84Hurt
use UniTriSplat rasterizer instead of OP43DGS on fisheyeUniTriSplat · FIORD (fisheye)PSNR (dB): 21.64 -> 24.27Improved
use UniTriSplat instead of OmniGSUniTriSplat · OmniBlenderPSNR (dB): 33.21 -> 32.57Hurt
use UniTriSplat instead of vanilla 3DGSUniTriSplat · Mip-NeRF 360 (perspective)PSNR (dB): 25.59 -> 27.57Improved
render perspective views from UniTriSplat-trained scene rather than 3DGS-renderedUniTriSplat · OmniBlender cross-cameraPSNR (dB): 22.54 -> 28.17Improved

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.

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