AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Implicit 4D Gaussian Splatting for Fast Motion with Large Inter-Frame Displacements

Seung-gyeom Kim, Areum Kim, Yongjae Yoo, Sukmin Yun

ICLR 2026 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting · 0 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 spatiotemporal slicing (ablation)SPIN-4DGS · Panoptic FootballPSNR: 27.48 -> 28.96Improved
add spatiotemporal slicing (ablation)SPIN-4DGS · Panoptic Footballtrain cost: 18GB -> 9GBImproved
add trainable positions to hash encoder (ablation)SPIN-4DGS network · Panoptic BasketballPSNR: 18.64 -> 19.17No clear effect
add input position normalization (ablation)SPIN-4DGS network · Panoptic BasketballPSNR: 19.17 -> 29.89Improved
replace ReLU with GELU (ablation)SPIN-4DGS network · Panoptic BasketballPSNR: 29.89 -> 30.05Improved
enlarge hash map from 2^21 to 2^23 (ablation)SPIN-4DGS network · Panoptic BasketballPSNR: 30.05 -> 30.25Improved
extend early Realtime-4DGS training from 15K to 30K iterations (ablation)SPIN-4DGS positions · Panoptic BasketballPSNR: 29.57 -> 29.39Hurt
increase refinement from 0.5K to 2K iterations (ablation)SPIN-4DGS · Panoptic BasketballPSNR: 29.86 -> 30.05Improved
apply SPIN-4DGS attribute learning to D3DGS positionsD3DGS · Panoptic SoftballPSNR: 28.43 -> 30.92Improved
apply SPIN-4DGS attribute learning to Realtime-4DGS positionsRealtime-4DGS · Panoptic BasketballPSNR: 27.89 -> 29.57Improved
apply SPIN-4DGS attribute learning to Realtime-4DGS positionsRealtime-4DGS · Panoptic BoxesSSIM: 0.93 -> 0.92Hurt
use SPIN-4DGS instead of Realtime-4DGSRealtime-4DGS · Neu3DVPSNR: 32.01 -> 32.19Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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