AI Paper Atlas

Research map / Video / Video segmentation and tracking

RealFlow: EM-Based Realistic Optical Flow Dataset Generation from Videos

Yunhui Han, Kunming Luo, Ao Luo, Jiangyu Liu, Haoqiang Fan, Guiming Luo, Shuaicheng Liu

ECCV 2022 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 32 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 realistic image pair rendering (RIPR) (ablation)RealFlow with RAFT · KITTI15 train (RF-Ktrain, 1 EM iteration)EPE: 3.93 -> 2.79Improved
render with RIPR instead of QVI interpolation (ablation)RealFlow with RAFT · KITTI15 train (RF-Ktrain, 1 EM iteration)EPE: 7.27 -> 2.79Improved
use softmax splatting instead of max splatting (ablation)RealFlow with RAFT · KITTI15 train (RF-Ktrain, 1 EM iteration)EPE: 3.03 -> 2.79Improved
use DPT depth instead of MiDaS (ablation)RealFlow with RAFT · KITTI15 train (RF-Ktrain, 1 EM iteration)EPE: 2.90 -> 2.79Improved
use DPT depth instead of bi-directional occlusion map (ablation)RealFlow with RAFT · KITTI15 train (RF-Ktrain, 1 EM iteration)EPE: 3.01 -> 2.79Improved
add bi-directional hole filling (BHF) vs no filling (ablation)RealFlow with RAFT · KITTI15 train (RF-Ktrain, 1 EM iteration)EPE: 2.95 -> 2.79Improved
use BHF instead of RFR inpainting (ablation)RealFlow with RAFT · KITTI15 train (RF-Ktrain, 1 EM iteration)EPE: 2.95 -> 2.79Improved
sample alpha from [0,2] instead of fixed 1 (ablation)RealFlow with RAFT · KITTI15 train (RF-Ktrain, 1 EM iteration)EPE: 3.38 -> 2.79Improved
run 4 EM iterations instead of 1 (ablation)RealFlow with RAFT · KITTI15 trainEPE: 2.79 -> 2.16Improved
train 4x longer on Iter.1 data instead of EM iterations (ablation)RealFlow with RAFT · KITTI15 trainEPE: 2.79 -> 2.86No clear effect
train RAFT on RF-AB instead of C+TRAFT · KITTI15 trainEPE: 5.04 -> 3.48Improved
train RAFT on RF-AB instead of C+TRAFT · Sintel Final trainEPE: 2.71 -> 3.28Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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