- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
ViGeo is a feed-forward model that predicts per-frame depth, normals and point maps from video. Its ViT-G, initialized from Depth Anything 3, uses dynamic chunking attention (DCA) across frames: full attention within a temporal chunk, causal across chunks, with chunk partitions randomized in training. One checkpoint therefore runs offline, streaming, or chunk-wise with a KV cache. Real-data labels are refined by a multi-frame depth completion teacher. Evaluation spans video, long-video and monocular depth, point maps and normals.
Critical strengths
- With negligible overhead, one unified checkpoint handles offline, streaming, and long-video inference—matching offline full-attention training (Sintel Rel 0.291 vs. 0.289) and surpassing online causal training (0.322 vs. 0.330, Table 5). This eliminates the conventional need to train dedicated models for each regime, such as VGGT and StreamVGGT.
- The appendix covers latency, chunk-size robustness and DCA post-training on other models.
Critical weaknesses
-
Questionable reliability of the state-of-the-art comparisons.
- Inconsistent baseline results: Under the same alignment protocol, the reported Sintel scores for Pi3, VGGT, and StreamVGGT are noticeably worse than those in their original publications (e.g., Pi3 degrades from 0.233 to 0.281), even though their Bonn and KITTI metrics match. Notably, Sintel is the exact benchmark where ViGeo claims its largest margin of improvement.
- Selective reporting: VGGT-Ω actually outperforms ViGeo on the Bonn dataset (0.043 vs. 0.046, as shown in Table 15), yet it is omitted from the main comparison tables.
-
The contributions are incremental, which limits significance.
- DCA (block-causal attention trained with random chunk sizes) is essentially U2/WeNet's dynamic chunk training from speech recognition, and MUSt3R (CVPR 2025) already runs one network offline and online. Neither is cited.
- In the ablations, DCA and the refined labels each change Rel by at most 0.008, so the gains likely come mainly from the DA3-Giant initialization and scale.
Questions for authors
- How was Sintel evaluated, and why do the baselines' Sintel numbers differ from published ones while Bonn and KITTI match? Which checkpoint produced each table (Table 8 uses an updated model)?
- In which coordinate frame are point maps evaluated in Table 4 (world-frame outputs of VGGT, StreamVGGT and STream3R would absorb pose error), and how are the multi-frame point clouds in Fig. 6 registered without predicted poses?
- What data trains the completion teacher, and does it overlap with the datasets it relabels?
- Minor suggestion (does not affect my rating): the related work could also discuss other feed-forward models that run online by reusing cached features of past frames, such as MUSt3R (CVPR 2025) and MoRe (CVPR 2026).