Research map / 3D vision / Depth and stereo
Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo
Read the paperCheck 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 |
|---|---|---|---|
| Evaluate with benchmark subsampling rather than all test pixels | Optical flow baselines on Spring · Spring test | 1px outlier rate: MS-RAFT+: 4.99 -> 5.72; FlowFormer: 6.12 -> 6.51; FlowNet2: 5.91 -> 6.71; RAFT: 6.05 -> 6.79; GMA: 6.30 -> 7.07; GMFlow: | Mixed |
| Pretrain on FlyingThings3D and then finetune on KITTI 2015 | Scene flow methods on Spring · Spring test | 1px outlier rate (total): M-FUSE: 34.90 -> 62.49; RAFT-3D: 78.82 -> 37.26; CamLiFlow: 50.08 -> 85.31 | Mixed |
Closest papers by meaning
- SEA-Flow3D: Simplified, Efficient, and Accurate Scene Flow via Spatial Vector Sampling and Multi-scale Refinement (CVPR 2026 · similarity 0.87)
- Zero-Shot Monocular Scene Flow Estimation in the Wild (CVPR 2025 · similarity 0.86)
- DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement (CVPR 2024 · similarity 0.85)
- Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video (ICLR 2025 · similarity 0.85)
- Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion (CVPR 2025 · similarity 0.85)
- Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations (NeurIPS 2025 · similarity 0.84)
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.