AI Paper Atlas

Research map / 3D vision / Depth and stereo

Taylor-Gaussians-Flow: Towards Non-uniform Motion for Novel View Synthesis from Monocular Video

Zaoming Yan, Qizhou Chen, Yaomin Huang, Pengcheng Lei, Chenhao Shi, Yi Xu, Haichuan Song, Faming Fang

ICML 2026 · 3D vision › Depth and stereo · approach: Learned optical and scene flow

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
use Taylor-Gaussians head with acceleration instead of velocity-only head (ablation)FF-TGsF · SNU-HARD 8 framesPSNR: 22.00 -> 25.19Improved
add second-order (acceleration) Taylor term (ablation)TGs-Flow · SNU-HARD 8 framesPSNR: 23.28 -> 25.19Improved
add first-order term over zero-order (ablation)TGs-Flow · SNU-HARD 8 framesPSNR: 19.71 -> 23.28Improved
add third-order supervision (ablation)TGs-Flow · SNU-HARD 8 framesstabilityHurt
add acceleration loss to RGB and flow losses (ablation)FF-TGsF · SNU-HARD 8 framesPSNR: 23.70 -> 24.86Improved
add optical-flow loss to RGB loss (ablation)FF-TGsF · SNU-HARD 8 framesPSNR: 20.33 -> 23.70Improved
add isotropic regularization (ablation)FF-TGsF · SNU-HARD 8 framesPSNR: 24.86 -> 25.19Improved
vary lambda_reg from 0.00 to 0.20 (ablation)FF-TGsF · SNU-HARD 8 framesPSNR: 25.13 (0.00), 25.10 (0.10), 25.06 (0.20)No clear effect
tune lambda_f and lambda_a (ablation)FF-TGsF · SNU-HARD 8 framesPSNR: 24.69 to 25.10No clear effect
train optical flow estimator on more datasets (ablation)FF-TGsF · SNU-HARD 8 framesPSNR: 23.61 -> 28.63Improved
add second-order term to flow supervision (ablation)TGs-Flow · Sintel final testEPE: 2.57 -> 2.04Improved
use FF-TGsF instead of NoPoSplat on RE10K novel viewFF-TGsF · RE10K novel viewPSNR: 28.65 -> 26.63Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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