- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper presents a cost-free stereo disparity estimation method. It adopts the initialization + iterative refinement architecture to regress disparity from coarse to fine. The method mainly follows the WAFT-Stereo. It presents performance on common benchmarks; however, the performance does not reach state of the art performance.
Critical strengths
None
Critical weaknesses
- This method is very similar to WAFT-Stereo in the overall architecture, without discussion about its sharp distinction. Moreover, the performance still falls behind WAFT-Stereo considerably in KITTI and cross-domain generation (where WAFT-Stereo is excluded from comparison without any statement).
- The presentation does not clearly describe how binocular views are processed by the encoder? They are concatenated along channel dimension, summed, or processed by the encoder independently and then concatenated? This very important architecture design is missing from the paper.
- The network presentation gives little information: the HSR encoder is a very common 4-stage backbone design, widely used recent networks like Swin Transformer, ConvNext; the HDP head fuses the 4-stage features of different resolutions like DPT head, although called a different name.
- The performance is not good. Cross-domain generalization falls significantly behind SOTA methods like WAFT-Stereo and FoundationStereo. Besides, the comparison with previous methods like BridgeDepth is unfair without indication, which only trained on SceneFlow dataset. Benchmark results on SceneFlow and KITTI are also not satisfying.
Questions for authors
- How does the HSR encoder process the binocular views?
- What's the core distinction between WAFT-Stereo?