- Rating
- 2
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes Temporal Subspace Distillation (TSD) to reduce motion degradation in few-step video distillation. It separates generated videos into temporal means and deviations, adding appearance and motion constraints to DMD. Experiments on Wan2.1 show improvements in overall video quality and motion preservation over DMD and adapted AVD baselines.
Critical strengths
- Practical motivation. The paper addresses an important trade-off in video distillation: visual details can improve while motion deteriorates.
- Structured design with empirical support. Temporal decomposition enables separate appearance and motion constraints. Experiments across multiple seeds and initialization settings support quality improvements without additional inference steps.
Critical weaknesses
- Missing comparisons with relevant recent methods. The experiments mainly compare against DMD and adapted AVD baselines, without clearly establishing comparisons to Causal-rCM[1] or SGMD[2]. Causal-rCM offers a closely related causal few-step generation setting, while SGMD provides an alternative approach to video distillation optimization. Their absence limits evidence that TSD’s temporal decomposition and auxiliary losses offer advantages over recent methods. The relationship between CF++ and Causal-rCM also needs clarification.
- Insufficient justification of the auxiliary components. The ablations show mixed benefits: adding VF to IA+MF lowers both benchmark means in Table 2, and adding MSW to TSD-B does the same in Table 5. Although the paper highlights gains from joint use, it provides limited analysis of these interactions and trade-offs. The need for the full design over simpler variants therefore remains unclear.
Questions for authors
- Does CF++ incorporate Causal-rCM, and if so, which components? Could you provide comparisons with Causal-rCM and SGMD using matched backbones, inference steps, and comparable training budgets, or explain the constraints preventing a fair comparison?
- What explains the lower scores when adding VF to IA+MF or MSW to TSD-B? Could paired per-seed results and motion-specific metrics clarify whether these changes reflect training variability or trade-offs between appearance and motion?
- What supports choosing the full configurations over simpler alternatives? IA+MF scores higher than TSD-B on VBench-1, while TSD-B scores higher than TSD-D on VBench-2. Could you clarify the selection criteria and sensitivity to the auxiliary loss weights?
[1] Zheng K, He G, Zhao M, et al. Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models[J]. arXiv preprint arXiv:2606.25473, 2026.
[2] Wu Z, Gong R, Yong Y, et al. SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation[J]. arXiv preprint arXiv:2605.30116, 2026.