AI Paper Atlas

Research map / 3D vision / Depth and stereo

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases

Matteo Poggi, Fabio Tosi

ICCV 2025 · 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
add BaseNet with motion bases from depth foundation model (ablation)SEA-RAFT (S) · TartanAir val (100K-step ablation)EPE: 1.38 -> 1.04Improved
add depth features to the BaseNet configuration (ablation)FlowSeek (T) · KITTI 2012 train (TartanAir-trained ablation)Fl-All: 4.23 -> 4.16Improved
add depth input to ContextNet on top of BaseNet and features (ablation)FlowSeek (T) · KITTI 2012 train (TartanAir-trained ablation)Fl-All: 4.16 -> 4.19No clear effect
use motion bases instead of raw depth map as BaseNet input (ablation)FlowSeek (T) · TartanAir val (100K-step ablation)EPE: 1.05 -> 1.03Improved
use motion bases instead of depth map after fine-tuning on KITTI 2015 (ablation)FlowSeek (T) · KITTI 2015 val dynamic regionsFl-EPE: 2.49 -> 2.60Hurt
use motion bases instead of depth map after fine-tuning on KITTI 2015 (ablation)FlowSeek (T) · KITTI 2015 val static regionsFl-EPE: 1.21 -> 1.06Improved
scale from small (12 iters) to medium (ResNet-34, Depth Anything v2 B, 4 iters) (ablation)FlowSeek · TartanAir val (100K-step ablation)EPE: 0.99 -> 0.90Mixed
run 12 iterations instead of 4 with ResNet-34 (ablation)FlowSeek (M) to (L) · TartanAir val (100K-step ablation)EPE: 0.90 -> 0.85Improved
use Depth Anything v2 instead of DPT-Hybrid (ablation)FlowSeek (T) · TartanAir val (100K-step ablation)EPE: 1.08 -> 1.03Improved
add FlowSeek priors to CRAFT backboneCRAFT · TartanAir val (100K-step ablation)EPE: 1.77 -> 1.39Improved
add FlowSeek priors to FlowFormer backboneFlowFormer · TartanAir val (100K-step ablation)EPE: 1.63 -> 1.30Improved
train SEA-RAFT (L) on a single GPU instead of original budgetSEA-RAFT (L) · KITTI 2015 train (TartanAir pretrain zero-shot)Fl-all: 12.7 -> 13.5Hurt

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