Research map / 3D vision / Depth and stereo
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add a 1D horizontal correlation layer (ablation) | DispNet · KITTI 2012 and KITTI 2015 train; Driving, FlyingThings3D, Monkaa, and Sintel Clean | Disparity EPE: KITTI 2012: 2.38 -> 1.75; KITTI 2015: 2.19 -> 1.59; Driving: 15.62 -> 16.12; FlyingThings3D: 2.02 -> 1.68; Monkaa: 5.99 | Mixed |
| Fine-tune on KITTI (ablation) | DispNetCorr1D · KITTI 2012 and KITTI 2015 train | Disparity EPE: KITTI 2012: 1.75 -> 1.48; KITTI 2015: 1.59 -> 1.48 | Helped |
| Fine-tune on KITTI (ablation) | DispNetCorr1D · Driving, FlyingThings3D, Monkaa, and Sintel Clean | Disparity EPE: Driving: 16.12 -> 20.40; FlyingThings3D: 1.68 -> 7.46; Monkaa: 5.78 -> 14.93; Sintel Clean: 5.66 -> 21.88 | Hurt |
| Add convolutions between up-convolutional layers (ablation) | DispNet architecture · KITTI 2015 | Relative EPE: roughly 15 % | Helped |
Closest papers by meaning
- Learning Optical Flow From Still Images (CVPR 2021 · similarity 0.91)
- LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation (CVPR 2018 · similarity 0.89)
- Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion (CVPR 2021 · similarity 0.89)
- Recurrent Partial Kernel Network for Efficient Optical Flow Estimation (AAAI 2024 · similarity 0.87)
- DepthFM: Fast Generative Monocular Depth Estimation with Flow Matching (AAAI 2025 · similarity 0.86)
- Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations (CVPR 2025 · similarity 0.86)
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.