Pith. sign in

REVIEW 5 cited by

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1512.02134 v1 pith:PFLIQT5V submitted 2015-12-07 cs.CV cs.LGstat.ML

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

Nikolaus Mayer , Eddy Ilg , Philip H\"ausser , Philipp Fischer , Daniel Cremers , Alexey Dosovitskiy , Thomas Brox This is my paper
classification cs.CV cs.LGstat.ML
keywords flowestimationconvolutionaldatasetsdisparitynetworksscenelarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluating scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MinNav: Minimalist Navigation Using Optical Flow For Active Tiny Aerial Robots

    cs.RO 2026-06 unverdicted novelty 6.0

    MinNav achieves 70% success navigating static/dynamic obstacles and unknown gaps on tiny aerial robots using only monocular optical flow and active exploration, claimed as the first such solution without prior knowledge.

  2. Attention-Guided Dual-Stream Learning for Group Engagement Recognition: Fusing Transformer-Encoded Motion Dynamics with Scene Context via Adaptive Gating

    cs.CV 2026-04 unverdicted novelty 6.0

    DualEngage fuses transformer-encoded student motion dynamics with 3D scene features via softmax-gated fusion to recognize group engagement in classroom videos, reporting 96.21% average accuracy on a university dataset.

  3. SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data

    cs.CV 2026-04 conditional novelty 6.0

    SynFlow creates a 34-times larger synthetic LiDAR scene flow dataset that lets models trained only on simulation match or beat supervised real-data baselines on multiple benchmarks.

  4. MegaFlow: Zero-Shot Large Displacement Optical Flow

    cs.CV 2026-03 accept novelty 6.0

    MegaFlow reaches SOTA zero-shot optical flow (especially large motions) and competitive point tracking by global matching of pre-trained ViT features followed by lightweight multi-frame refinement.

  5. Scene Motion Decomposition for Learnable Visual Odometry

    cs.CV 2019-07 unverdicted novelty 5.0

    Decomposing scene motion into per-point 6DoF motion maps from optical flow and depth enables a neural network to estimate camera motion more accurately than stacking raw inputs.