AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MoRel: Long-Range Flicker-Free 4D Motion Modeling via Anchor Relay-based Bidirectioanl Blending with Hierarchical Densification

Sangwoon Kwak, Weeyoung Kwon, Jun Young Jeong, Geonho Kim, Won-Sik Cheong, Jihyong Oh

CVPR 2026 · 3D vision › Gaussian splatting · approach: Deformable 4D 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 key-frame anchors (local canonical spaces) to a single global anchor model (ablation)MoRel baseline · SelfCap_LR 300-frame subsetLPIPS: 0.386 -> 0.364Improved
add key-frame anchors with on-demand loading (ablation)MoRel baseline · SelfCap_LR 300-frame subsettraining memory (MB): ~12,000 -> ~4,500Improved
add key-frame anchors (ablation)MoRel baseline · SelfCap_LR 300-frame subsetSSIM: 0.654 -> 0.647Hurt
add PWD and linear blending between adjacent KfAs (ablation)MoRel · SelfCap_LR 300-frame subsetPSNR: 19.90 -> 20.66Improved
replace linear blending with learnable temporal opacity (IFB) (ablation)MoRel · SelfCap_LR 300-frame subsetPSNR: 20.66 -> 21.07Improved
add feature-variance-guided hierarchical densification (FHD) (ablation)MoRel · SelfCap_LR 300-frame subsetPSNR: 21.07 -> 21.20 PSNR; LPIPS 0.342 -> 0.348Mixed
use chunk-based training of 4DGS instead of all-at-once4DGS · SelfCap_LRtOF: 0.222 -> 0.680Hurt
use MoRel anchor relay and bidirectional blending versus all-at-once 4DGS4DGS · SelfCap_LR (average)PSNR: 18.95 -> 21.00Improved
use MoRel on a standard short benchmarkMoRel · DyNeRFPSNR: 31.75 vs 31.06No clear effect
use multi-stage MoRel training instead of single-stage 4DGS4DGS · SelfCap_LR Bike_1training time (h): 10h -> 16.5hHurt

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