AI Paper Atlas

Research map / 3D vision / Depth and stereo

CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation

Haisong Liu, Tao Lu, Yihui Xu, Jia Liu, Wenjie Li, Lijun Chen

CVPR 2022 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 68 citations (OpenAlex)

Check 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 bidirectional fusion instead of the best unidirectional fusion (ablation)CamLiFlow · FlyingThings3D valEPE2D: 2.25 to 2.18Improved
Use bidirectional fusion instead of the best unidirectional fusion (ablation)CamLiFlow · FlyingThings3D valEPE3D: 0.036 to 0.033Improved
Fuse pyramid, cost-volume, and flow-decoder features at all three stages (ablation)CamLiFlow · FlyingThings3D valEPE2D: 2.29 to 2.18Improved
Add learnable nearest-neighbor interpolation to direct point projection (ablation)CamLiFlow Bi-CLFM · FlyingThings3D valEPE2D: 2.30 to 2.24Improved
Add 2D similarity measurements to interpolation (ablation)CamLiFlow Bi-CLFM · FlyingThings3D valEPE2D: 2.24 to 2.18Improved
Increase interpolation neighbors from k=1 to k=3 with MEAN or MAX aggregation (ablation)CamLiFlow Bi-CLFM · FlyingThings3D valEPE2D: 2.18; 2.19; 2.19No clear effect
Apply inverse depth scaling to point coordinates (ablation)CamLiFlow · FlyingThings3D valEPE3D: 0.036 to 0.033Improved
Apply inverse depth scaling to point coordinates (ablation)CamLiFlow LiDAR-only · FlyingThings3D valEPE3D: 0.073 to 0.068Improved
Add background rigidity refinement (ablation)CamLiFlow · KITTI Scene Flow testSF-all: 5.62 to 4.43Improved
Omit robust-loss fine-tuning (ablation)CamLiFlow · FlyingThings3D valACC1px: 84.3% to 87.3%Hurt
Detach gradients between modality branches in Bi-CLFM (ablation)CamLiFlow · FlyingThings3D val3D branch performanceImproved
Add batch normalization to the feature pyramid (ablation)CamLiFlow · Trainingtraining stabilityImproved

Later papers that compared with this method

4 later accepted papers report CamLiFlow as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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