AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Seele: A Unified Acceleration Framework for Real-Time Gaussian Splatting on Mobile Devices

He Zhu, Xiaotong Huang, Zihan Liu, Weikai Lin, Xiaohong Liu, Zhezhi He, Jingwen Leng, Minyi Guo, Yu Feng

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting

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 hybrid preprocessing (view-dependent representation plus online filtering) to code-optimized 3DGS (ablation)3DGS on Orin AGX · Mip-NeRF360FPS: 21.75 -> 46.15Improved
add contribution-aware rasterization to code-optimized 3DGS (ablation)3DGS on Orin AGX · Mip-NeRF360FPS: 21.75 -> 30.10Improved
add hybrid preprocessing (ablation)3DGS on Orin AGX · Mip-NeRF360PSNR: 27.46 -> 27.70Improved
add contribution-aware rasterization (ablation)3DGS on Orin AGX · Mip-NeRF360PSNR: 27.46 -> 27.50No clear effect
add code optimizations (fine-grained fetching, overlap) (ablation)3DGS on Orin AGX · Mip-NeRF360FPS: 20.79 -> 21.75Improved
fine-tune with consistency loss instead of extra training with the original loss (ablation)SEELE + 3DGS · Mip-NeRF360PSNR: 27.48 -> 27.72Improved
add Lconsistency (FLIP) to fine-tuning (ablation)SEELE + 3DGS · Tanks&TemplesFLIP7 view consistency: 0.074 -> 0.067Improved
add Lconsistency (FLIP) to fine-tuning (ablation)SEELE + 3DGS · Deep BlendingFLIP7 view consistency: 0.043 -> 0.042Improved
apply SEELE to four 3DGS pipelines3DGS, MiniSplatting, LightGaussian, AdR-Gaussian · Mip-NeRF360, Tanks&Temples, Deep Blendingspeedup: 3.2x, 1.8x, 2.7x, 1.7x average speedupImproved
apply SEELE to lower-power GPU (Orin NX) vs workstation GPU3DGS · Mip-NeRF360FPS: 3.06 -> 9.42 (Orin NX); 134.45 -> 328.98 (A6000)Improved
increase pixel group size beyond 2x4 (ablation)contribution-aware rasterization · Mip-NeRF360PSNRHurt
use 8 clusters with 8 neighbors (ablation)hybrid preprocessing · Mip-NeRF360PSNRHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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