AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Learning Implicit Constitutive Laws for Dynamic 3D Gaussian Splatting from Monocular Videos

Xiaoyang Liu, Kai Han

ECCV 2026 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction

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 GCA (vs NeuMA)NeuMA · Synthetic benchmarkaverage Chamfer Distance: 0.954 -> 0.496Improved
add rank-based depth anchors (RDGA) (ablation)GCA · Synthetic (Elastomer Ball)Chamfer Distance: 3.842 -> 0.922Improved
add global alignment term (ablation)GCA · Synthetic benchmarkChamfer Distance: >100 -> 0.922Improved
use rank-based loss instead of L1 depth loss (ablation)GCA · Synthetic benchmarkaverage Chamfer Distance: 0.844 -> 0.496Improved
add anchor supervision (ablation)GCA · Synthetic (Plasticine Cat)Chamfer Distance: 0.510 -> 0.318Improved
add Constitutive Prior Regularizer (CPR) (ablation)GCA · Synthetic (Elastomer Ball)Chamfer Distance: 1.024 -> 0.922Improved
add CPR (ablation)GCA · Synthetic (Gel Duck)Chamfer Distance: 0.694 -> 0.702No clear effect
use LoRA instead of full fine-tuning (ablation)GCA · Efficiency comparisonChamfer Distance: 1.35 -> 0.50Improved
add monocular depth supervision to PAC-NeRF (ablation)PAC-NeRF · Monocular setting (Ball, Cat)Chamfer Distance: 0.85 -> >100Hurt
remove target law from CPR library (ablation)GCA · Synthetic (Plasticine Cat)Chamfer Distance: 0.318 -> 0.397Hurt
remove target law from CPR library (ablation)GCA · Synthetic (Elastomer Ball)Chamfer Distance: 0.922 -> 0.976Hurt
use GCA instead of NeuMA for law recoveryNeuMA · JellyDuck constitutive responseresponse error (%): 39.6 -> 8.0Improved

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