AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting

Tingxuan Huang, Haowei Zhu, Jun-Hai Yong, Hao Pan, Bin Wang

ICLR 2026 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting · 2 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 control nodes with spatial k-NN only (no learned affinity) (ablation)single-frame baseline · HyperNeRF (ablation setting)PSNR: 25.15 -> 24.52Hurt
decouple node position and code with learned affinity (ablation)Mango-GS with nodes · HyperNeRF (ablation setting)PSNR: 24.52 -> 25.31Improved
go multi-frame with temporal MLP layers (ablation)Mango-GS · HyperNeRF (ablation setting)PSNR: 25.31 -> 27.30Improved
add temporal self-attention to multi-frame network (ablation)Mango-GS · HyperNeRF (ablation setting)PSNR: 27.30 -> 27.78Improved
add top-k hard-frame loss (ablation)Mango-GS · HyperNeRF (ablation setting)PSNR / tLPIPS: PSNR 27.78 -> 28.05; tLPIPS 0.0196 -> 0.0202Mixed
add motion-aware loss (ablation)Mango-GS · HyperNeRF (ablation setting)PSNR / tLPIPS: PSNR 28.05 -> 28.32; tLPIPS 0.0202 -> 0.0192Improved
increase time window from 6 to 8 (ablation)Mango-GS · HyperNeRF (ablation setting)PSNR: 28.35 -> 28.24Hurt
reduce time window from 6 to 2 (ablation)Mango-GS · HyperNeRF (ablation setting)PSNR: 28.35 -> 27.53Hurt
use K=5 neighbors instead of K=3 (ablation)Mango-GS · HyperNeRF (ablation setting)PSNR: 28.39 -> 27.90Hurt
increase initial nodes from 2048 to 4096 (ablation)Mango-GS · HyperNeRF (ablation setting)PSNR: 28.32 -> 28.25No clear effect
use only sparse stride sampler instead of 0.7:0.3 mix with interpolation sampler (ablation)Mango-GS · HyperNeRF-vrigPSNR: 26.2 -> 25.4Hurt
raise interpolation sampler ratio to 0.5 (ablation)Mango-GS · HyperNeRF-vrigPSNR: 26.2 -> 25.6Hurt

Later papers that compared with this method

1 later accepted paper reports MangoGS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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