Research map / 3D vision / Depth and stereo
LiteMatch: Lightweight Zero-Shot Stereo Matching via Cost Volume Stabilization
Md Raqib Khan, Santosh Kumar Vipparthi, Subrahmanyam Murala
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 |
|---|---|---|---|
| add CVC-Loss (ablation) | LiteMatch baseline · Scene Flow | EPE: 0.98 -> 0.84 | Improved |
| add CVC-Loss (ablation) | LiteMatch baseline · Scene Flow | D1 (%): 4.48 -> 3.30 | Improved |
| add High-Frequency Encoder (HFE) (ablation) | LiteMatch + CVC-Loss · Scene Flow | EPE: 0.84 -> 0.70 | Improved |
| add cross-attention (CA) (ablation) | LiteMatch + HFE · Scene Flow | EPE: 0.70 -> 0.65 | Improved |
| add cost volume refinement (ablation) | LiteMatch + HFE + CA · Scene Flow | EPE: 0.65 -> 0.59 | Improved |
| add Correspondence Encoder (Corr) (ablation) | LiteMatch + refinement · Scene Flow | EPE: 0.59 -> 0.53 | Improved |
| add iterative refinement (IR) head (ablation) | LiteMatch (Base) · Scene Flow | D1 (%): 2.29 -> 1.92 | Improved |
| add HFE (edge regions) (ablation) | LiteMatch · Scene Flow | D1 (%): 9.45 -> 7.21 | Improved |
| add HFE (edge regions) (ablation) | LiteMatch · DrivingStereo (zero-shot) | D1 (%): 10.62 -> 8.24 | Improved |
| use CVC-Loss instead of categorical CE (ablation) | LiteMatch Stage 1 · Scene Flow | D1 (%): 3.25 -> 2.29 | Improved |
| use CVC-Loss instead of focal loss (ablation) | LiteMatch Stage 1 · Scene Flow | D1 (%): 2.91 -> 2.29 | Improved |
| add iterative refinement head (more iterations vs MonSter) | LiteMatch · KITTI-2015 (zero-shot) | Bad3.0 (%): 4.09 vs 4.00 (MonSter) | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- MonSter — MonSter: Marry Monodepth to Stereo Unleashes Power (CVPR 2025) · better on 5 of 9 shared results
- Mocha-Stereo — MoCha-Stereo: Motif Channel Attention Network for Stereo Matching (CVPR 2024) · better on 2 of 2 shared results
- DEFOM-Stereo — DEFOM-Stereo: Depth Foundation Model Based Stereo Matching (CVPR 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Lite Any Stereo: Efficient Zero-Shot Stereo Matching (CVPR 2026 · similarity 0.93)
- Generalized Geometry Encoding Volume for Real-time Stereo Matching (AAAI 2026 · similarity 0.90)
- Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail (CVPR 2025 · similarity 0.90)
- FoundationStereo: Zero-Shot Stereo Matching (CVPR 2025 · similarity 0.89)
- MonSter: Marry Monodepth to Stereo Unleashes Power (CVPR 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.
