- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes PhasePose, an upsampling-free top-down estimator for pose estimation in low-resolution feature maps. Authors combine Haar analysis, SO(3) rotation, DCT, Simcc and etc for pose estimation. Experiments are preformed on COCO, MPII, and others.
Critical strengths
- Experimental results show that the method achieves good performance.
- Authors perform ablation studies.
Critical weaknesses
- The motivation for this paper appears somewhat weak. The authors claim to address the problem of low-resolution pose estimation but directly employ a large number of frequency-domain-related components, such as Haar analysis, DCT, and SO(3). Why are these techniques relevant to the problem at hand?
- Although the frequency domain is presented as the primary approach to solving the low-resolution feature problem, the authors actually utilize frequency-domain information from an earlier stage, which does not demonstrate the effectiveness of the proposed frequency-domain analysis for low-resolution scenarios.
- The decoupling of feature map resolution from output coordinate accuracy is already a key premise of coordinate-based classification methods such as SimCC. It is unfair to use this as a basis for analyzing the degradation of heatmaps, since heatmaps inherently benefit from high resolution.
- For low-resolution results, the backbones used by different methods vary. Can the authors provide results based on HRNet or the VIT backbone?
- The overall framework is complex and lacks intuitiveness.
Questions for authors
- Please clarify the motivation more deeply.
- Please provide experimental results using frequency information from low resolution feature maps.
- Please provide the results under different backbone.
- There seems to be a problem with the citation format, which makes the paper difficult to read.
2 comments
Response to Reviewer nmZy (Part 2/2): Low-Resolution Frequency Analysis, New ViT-S Results, and Ongoing Experiments
We thank the reviewer again for the constructive suggestion on low-resolution Vision Transformer evaluation. Following up on our previous response, we have completed the controlled 64x48 comparison on the ViT-S backbone and updated Table 2 and Appendix B.1 in the uploaded revision.
New Controlled Low-Resolution ViT-S Experiment (64x48, COCO val2017)
- Identical Backbone and Bit-Exact Initialization: Both
PhasePose ViT-Sand theViTPose-S s8 DARKbaseline use the identicalmmpretrain.VisionTransformerViT-Small backbone (12 layers,embed_dims=384, 12 heads, MLP width 1536) withpatch_size=16andpatch_cfg=dict(stride=8, padding=4). At64x48input resolution, both output an identical8x6feature map with 384 channels, and all 149 backbone initialization tensors are verified bit-for-bit identical. Both models use the exact same training schedule and evaluation protocol (flip_test=Truefor AP; batch-1 FP32 eager timing for latency). - Neck and Head Comparison:
- PhasePose ViT-S: Uses a parameter-free
PhasePosePoolNeckthat routes the8x6(stride-16) feature map directly as the detail/phase branch and applies2x2average pooling to form the4x3(stride-32) semantic branch, followed byPhasePoseV2Head(embed_dim=256, 8 heads, 4 visual blocks,PixelUnshuffle(2)detail injection, 3-step recurrent phase correction withspectral_dim=96and OKS coupling) predicting 1D SimCC logits (96x128bins, split ratio2.0) trained withKLDiscretLoss + OKSLossand decoded via 1D DARK. - ViTPose-S s8 DARK: Connects the
8x6backbone feature directly (no neck) to aHeatmapHeadwith twoConvTranspose2d(kernel=4, stride=2, ch=256)layers and a1x1conv, upsampling 4x to24x322D heatmaps (17 channels) trained withKeypointMSELoss + MSRAHeatmap(unbiased=True)and evaluated with 2D DARK second-order Taylor decoding.
- PhasePose ViT-S: Uses a parameter-free
| Method | Backbone | Input | Params | FLOPs | CPU (ms) | GPU (ms) | AP |
|---|---|---|---|---|---|---|---|
| ViTPose-S s8 DARK | ViT-S | 64x48 | 24.2M (24.235M) | 1.3G (1.338G) | 17.7 | 5.1 | 53.4 |
| PhasePose (ours) | ViT-S | 64x48 | 27.0M (26.988M) | 1.2G (1.169G) | 17.1 | 5.3 | 58.9 (+5.5) |
Under bit-for-bit identical backbone initialization, PhasePose ViT-S reaches 58.9 AP (0.5894), outperforming ViTPose-S s8 DARK (53.4 AP) by +5.5 AP. Although the recurrent phase head adds 2.75M parameters, operating on the 4x3 grid and 1D coordinate sequences avoids 2D transposed convolutions over 16x12 -> 32x24 spatial grids, reducing FLOPs by 12.6% (1.169G vs. 1.338G, i.e., ViTPose-S uses 14.5% higher FLOPs) and improving CPU latency (17.1 ms vs. 17.7 ms). Thank you again for this helpful suggestion.
Response to Reviewer nmZy (Part 1/2): Motivation, Heatmap Fairness, and Presentation Clarity
We sincerely thank the reviewer for the constructive comments regarding our motivation, frequency-domain design, fairness of heatmap comparisons, backbone diversity, and presentation clarity. We have uploaded a revised manuscript and supplementary PDF addressing your feedback, and we are also running additional experiments on deepest-stage frequency analysis and low-resolution ViT/HRNet backbones, which we will report in a follow-up comment during the discussion period. Due to the character limit, Part 1 addresses Weaknesses 1, 3 & 5 and Questions 1 & 4; Part 2 addresses Weaknesses 2 & 4 and Questions 2 & 3.
1. Fair Motivation Without Heatmap-Degradation Premise (Weakness 3 & Question 1)
We completely agree with the reviewer that decoupling coordinate precision from feature-map resolution is already a core premise of SimCC, and that using heatmap degradation on tiny grids as the main motivation is unfair because heatmaps inherently benefit from high spatial resolution.
In the uploaded revision, we removed the heatmap degradation study from the main paper (moving it to Appendix A solely as supplementary context) and rewrote Section 1 starting directly from coordinate classification: while SimCC eliminates spatial grid quantization, simply increasing the number of 1D output bins neither restores local directional contrasts lost during downsampling nor distinguishes a flat unimodal spread from multimodal ambiguity under occlusion.
2. Why Haar + SO(3) and DCT Are Relevant and Intuitive (Weaknesses 1 & 5, Question 1)
Rather than combining unrelated frequency tools, our two modules form a direct, intuitive closed loop (Section 3, illustrated step-by-step in Figures 2 and 3):
48.1%energy share; reducing inter-band correlation from0.31to0.03in Figure 1). A lightweight 24-scalar groupedSO(3)rotation then adapts the 3-band detail basis to task-relevant limb orientations without upsampling the grid (Table 5: +0.77 mean AP over no detail memory across 5 seeds).argmaxon initial SimCC logits discards distribution shape. A truncated DCT-II basis (with a zero-start low-rank adapter) compresses the full 1D coordinate distribution into a compact state vector (Table 4(b): +1.06 AP over coordinates alone), while distribution entropy explicitly routes cross-attention toward the cached directional-detail bands when predictions are uncertain (Figure 5: 2.25x, 1.94x, and 2.34x near-target attention enrichment in detail bands D1-D3 across 1,499 joints, vs. 0.67x in Main).3. Citation Formatting and Readability Improvements (Question 4 & Presentation)
Thank you for catching the citation formatting issue: bare
\citecommands undernatbibauthor-year style broke sentence flow in the initial submission. We have audited and corrected all citations to proper parenthetical and textual\citep/\citetformatting throughout the revised paper, streamlined the exposition in Sections 1 and 3, and added a dedicated step-by-step diagram of the shared recurrent corrector (Figure 3) to make the framework easy to follow.