- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
QuadVGGT accelerates long-sequence VGGT-based 3D reconstruction and reduces memory usage by sharing query and key-value attention computations through anchor-guided representatives while preserving dense token representations and geometric accuracy.
Critical strengths
I think the proposed acceleration method is thoughtfully designed by jointly considering the underlying computational mechanics of attention and the unique characteristics of 3D reconstruction. The method is simple, well-motivated, and effective. The authors also provide extensive experiments to substantiate their claims, and I have carefully examined the appendix as well.
Critical weaknesses
- The 500- and 1,000-frame experiments are primarily conducted on densely sampled sequences with small inter-frame motion and substantial visual overlap. However, the method is not evaluated on genuinely large-scale, long-range capture sequences, such as those commonly used to benchmark SLAM systems. Consequently, the current experiments mainly demonstrate that the proposed acceleration is effective for highly redundant inputs, but do not establish its robustness in long-sequence settings involving broad spatial coverage, large viewpoint changes, or limited frame overlap.
- Table 5 shows that the memory reduction mainly comes from HFO rather than Quotient Attention. Since this technique could also be applied to other methods, the memory comparison may not be fully fair. Applying the same offloading strategy to the baselines would provide a more controlled comparison.
Questions for authors
Please check the weaknesses and answer my questions.
4 comments
Author Response 2/N
Question 2 : Is the memory comparison fair without applying the same HFO strategy to the baselines?
We thank the reviewer for this suggestion and agree that a controlled memory comparison is necessary. Quotient Attention and HFO address independent bottlenecks: the former reduces attention computation, while the latter offloads intermediate features retained by VGGT-style prediction heads. Since these heads consume four intermediate layers only after the final block, we applied the same HFO strategy to dense VGGT and all five baselines without modifying their attention. Only feature storage and restoration were changed, and outputs remain bit-identical (Table R9).
The memory savings confirm that HFO addresses a common architectural bottleneck: approximately 24 GB for dense VGGT and FlashVGGT (fp32), and 11.9 GB for FastVGGT and LiteVGGT (bf16). HFO also enables SparseVGGT and SAF3R to complete all 7-Scenes sequences at 1,000 frames, where they previously failed.
With HFO applied equally, QuadVGGT's peak memory falls within the baseline range, separating HFO's memory contribution from that of Quotient Attention. Importantly, QuadVGGT remains the fastest method, achieving 1.55× speedup over FlashVGGT, 2.26× over LiteVGGT, 2.02× over FastVGGT, and 14.55× over dense VGGT. Thus, the controlled comparison confirms that Quotient Attention provides the speed-up, while HFO provides architecture-independent memory savings. We will add Table R9 and clarify this attribution in the revision.
Table R9. Controlled comparison with HFO applied to every method (7-scene, N-BGRD, ScanNet 1000 frames)
| Method | HFO | Rel↓ | τ↑ | Acc↓ | Comp↓ | CD↓ | NC↑ | APE↓ | ARE↓ | RPE-T↓ | RPE-R↓ | Time (s)↓ | Mem (GB)↓ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VGGT | ✗ | .0313 | .9670 | .0119 | .0088 | .0104 | .6979 | .0548 | .0985 | .0083 | .0143 | 678.27 | 72.40 |
| ✓ | .0313 | .9670 | .0119 | .0088 | .0104 | .6979 | .0548 | .0985 | .0083 | .0143 | 666.43 | 48.5 | |
| FastVGGT | ✗ | .0383 | .9712 | .0134 | .0079 | .0101 | .6924 | .0459 | .0621 | .0058 | .0139 | 94.83 | 72.7 |
| ✓ | .0383 | .9712 | .0134 | .0079 | .0101 | .6924 | .0459 | .0621 | .0058 | .0139 | 92.74 | 60.8 | |
| LiteVGGT | ✗ | .0402 | .9690 | .0175 | .0089 | .0132 | .6504 | .0711 | .1313 | .0104 | .0184 | 108.77 | 51.1 |
| ✓ | .0402 | .9690 | .0175 | .0089 | .0132 | .6504 | .0711 | .1313 | .0104 | .0184 | 103.53 | 39.2 | |
| FlashVGGT | ✗ | .0301 | .9745 | .0115 | .0079 | .0097 | .6701 | .0403 | .0639 | .0053 | .0071 | 72.23 | 72.2 |
| ✓ | .0301 | .9745 | .0115 | .0079 | .0097 | .6701 | .0403 | .0639 | .0053 | .0071 | 70.77 | 48.4 | |
| SparseVGGT | ✗ | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM |
| ✓ | .0452 | .9238 | .0110 | .0097 | .0104 | .6182 | .0483 | .0680 | .0061 | .0085 | 532.76 | 69.6 | |
| SAF3R | ✗ | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM | OOM |
| ✓ | .0440 | .9238 | .0108 | .0094 | .0101 | .6244 | .0434 | .0652 | .0051 | .0069 | 183.58 | 69.7 | |
| QuadVGGT (Ours) | ✗ | .0274 | .9670 | .0087 | .0083 | .0085 | .7229 | .0362 | .0577 | .0058 | .0075 | 58.72 | 76.5 |
| ✓ | .0274 | .9670 | .0087 | .0083 | .0085 | .7229 | .0362 | .0577 | .0058 | .0075 | 45.80 | 55.9 |
Thanks for the response. The newly added experiments are useful for addressing my concerns.
We sincerely thank the reviewer for their positive feedback. We are glad that the additional experiments helped address your concerns. We greatly appreciate your constructive comments, which have helped us strengthen our work.
Author Response 1/N
Question 1 : How robust is QuadVGGT on large-scale, long-range sequences with substantial viewpoint changes and limited frame overlap?
We thank the reviewer for highlighting the need to evaluate QuadVGGT on long-range sequences with limited frame overlap and substantial viewpoint changes. This insightful suggestion prompted us to conduct an additional evaluation on KITTI Odometry 00–10, through which we uncovered an important aspect of QuadVGGT's adaptive behavior under challenging viewing conditions. KITTI is a standard outdoor SLAM benchmark covering kilometre-scale driving routes with limited overlap between consecutive views. We uniformly sample each sequence over its full length to at most 2,500 frames, further increasing the gap between consecutive inputs (Table R8).
On KITTI, QuadVGGT runs 11.3× faster than dense VGGT and is also faster than FlashVGGT, while using 27% less peak memory than both. It also achieves lower ATE, ARE, and RPE-R than FlashVGGT, with comparable RPE-T. Across all sequences, its worst-case ATE remains within 1.74× of dense VGGT, whereas FlashVGGT degrades by 13× on seq04. On ETH3D, QuadVGGT achieves camera-pose accuracy comparable to dense VGGT (Table 12(b)). Further ablations show that operator-induced assignments preserve near-dense accuracy, whereas simpler anchor and representative-selection strategies exhibit noticeable degradation (Table 14).
Importantly, these additional experiments reveal the adaptive nature of Delta-Walking. Unlike fixed-ratio methods such as FlashVGGT and FastVGGT, Delta-Walking adjusts the anchor budget according to scene redundancy. Specifically, a frame is selected as a new anchor when 1 − ⟨g_s, g_{a_last}⟩ > Δ* (Eq. (2)), where g_s is the normalized frame descriptor and a_last denotes the latest anchor. Using the same threshold (Δ* = 0.002), Delta-Walking retains approximately 2.5× more anchors on KITTI than on 7-Scenes, while anchors still account for only about 5% of the frames. Non-anchor tokens are assigned to representative tokens in nearby views observing the same structure, while preserving the original token representations of all frames for per-frame predictions. Thus, QuadVGGT adapts to limited overlap without sacrificing most of the attention reduction.
Although absolute errors remain high for all feed-forward models on kilometre-scale routes without loop closure, including dense VGGT, QuadVGGT closely preserves the dense model's behavior as frame overlap decreases. We will incorporate the KITTI evaluation and the corresponding discussion into the revised manuscript.
We sincerely appreciate the reviewer's insightful suggestion. It not only helped us strengthen the experimental evaluation but also led us to uncover and better understand an important characteristic of QuadVGGT's adaptive design. We are truly grateful for this valuable feedback.
Table R8. KITTI 00–10, 2,500 frames (mean of 11 sequences). Speed-up over VGGT in parentheses. Best values are shown in bold.