Research map / Video / Video segmentation and tracking
Temporally Consistent Stereo Matching
Jiaxi Zeng, Chengtang Yao, Yuwei Wu, Yunde Jia
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 changed | Where | Measured | Effect |
|---|---|---|---|
| initialize refinement from past disparity and hidden state directly (XR-Stereo style) instead of from scratch (ablation) | RAFT-Stereo (5 iterations) · TartanAir ablation, all regions | >1px (%): 8.04 -> 8.77 | Hurt |
| add temporal state fusion of completion-module state with past hidden state (ablation) | TC-Stereo · TartanAir ablation, all regions | >1px (%): 8.77 -> 6.98 | Improved |
| add temporal disparity completion (TDC) module (ablation) | TC-Stereo · TartanAir ablation, all regions | >1px (%): 6.98 -> 6.10 | Improved |
| add dual-space refinement module (ablation) | TC-Stereo · TartanAir ablation, occluded regions | >1px (%): 29.89 -> 25.89 | Improved |
| combine TDC and dual-space refinement (ablation) | TC-Stereo · TartanAir ablation, all regions | >1px (%): 6.10 -> 5.98 | Improved |
| extend training sequence length from 2 to 4 frames (ablation) | TC-Stereo · TartanAir ablation, all regions | >1px (%): 5.98 -> 5.84 | Improved |
| run TC-Stereo in single-frame mode (no temporal inputs at inference) (ablation) | TC-Stereo · TartanAir ablation, all regions | temporal jitter |Δd| (px): 0.20 -> 0.28 | Hurt |
| use TC-Stereo with 5 iterations instead of RAFT-Stereo with 32 iterations | RAFT-Stereo · TartanAir ablation, all regions | >1px (%): 6.02 -> 5.98 | Improved |
| increase RAFT-Stereo iterations from 5 to 32 without temporal modules (ablation) | RAFT-Stereo · TartanAir ablation, occluded regions | temporal jitter |Δd| (px): 1.15 -> 0.93 | Improved |
| use TC-Stereo instead of DLNR on SceneFlow EPE | TC-Stereo · SceneFlow | EPE (px): 0.47 -> 0.50 | Hurt |
Closest papers by meaning
- Stereo Any Video: Temporally Consistent Stereo Matching (ICCV 2025 · similarity 0.92)
- DispViT: Direct Stereo Disparity Regression with a Single-Stream Vision Transformer (ICLR 2026 · similarity 0.91)
- On the confidence of stereo matching in a deep-learning era: a quantitative evaluation (TPAMI 2021 · similarity 0.91)
- Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching (ECCV 2024 · similarity 0.90)
- PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching (NeurIPS 2025 · similarity 0.89)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.89)
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.
