AI Paper Atlas

Research map / 3D vision / Depth and stereo

LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow

Hongyu Wen, Erich Liang, Jia Deng

ECCV 2024 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 9 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
fine-tune RAFT jointly on synthetic LayeredFlow data and Sintel (S+L) (ablation)RAFT · LayeredFlow first layer, all pointsEPE: 16.49 -> 15.63Improved
fine-tune RAFT on Sintel only (ablation)RAFT · LayeredFlow first layer, all pointsEPE: 16.49 -> 17.94No clear effect
fine-tune RAFT on synthetic data only (L) vs adding Sintel (ablation)RAFT · LayeredFlow first layer, diffuseEPE: 10.76 -> 14.69 (L); 6.95 (S+L)Hurt
fine-tune RAFT on synthetic data for last-layer predictionRAFT · LayeredFlow last layer, behind transparentEPE: 8.48 -> 4.34Improved
fine-tune RAFT on synthetic data for last layerRAFT · LayeredFlow last layer, all pointsEPE: 8.28 -> 7.72Improved
fine-tune RAFT on synthetic data (L) for reflective first-layer points (ablation)RAFT · LayeredFlow first layer, reflectiveEPE: 8.51 -> 17.30Hurt
use multiple context encoders and layer heads (Multi-RAFT) instead of single-flow RAFTRAFT · Multi-layer bad-3px, all pointsbad-3px (%): 54.99 -> 48.98Improved
Multi-RAFT vs RAFT on diffuse surfacesMulti-RAFT (L) · Multi-layer bad-tau, diffusebad-3px (%): 24.57 -> 28.75Hurt
add Sintel to Multi-RAFT fine-tuning (S+L) at higher layers (ablation)Multi-RAFT · Multi-layer count-aware bad-tau, Layer 2 and 3bad-3px (%): 79.93 -> 74.93 (Layer 2); 88.50 -> 85.88 (Layer 3)Improved

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