- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes a conceptual framework that splits hallucination in video generation into two kinds of risk: 1) low-density sampling risk and 2) high-density drifting risk. Then training-free methods are proposed, aiming to reduce the risks. HA-Sampler adds gradient guidance from an external loss (WMReward's score) to latent refinement. HA-Scorer estimates a video's likelihood under the generator through a continuous-normalizing-flow computation for candidate selection. Experiments are conducted on Physics-IQ and VideoPhy.
Critical strengths
-
The method works with existing video models without retraining i.e. in a training-free manner.
-
It gives some consistent, although marginal sometimes, improvements on two benchmarks and different backbones.
Critical weaknesses
-
The two-risk formulation is like storytelling. It is highly conceptual, and too general to be wrong. It is not directly connected with the proposed method. This storytelling complicates the paper, and does not contribute much.
-
The proposed method is not specific to physical hallucinations. HA-Sampler is a standard combination of latent refinement and gradient guidance. HA-Scorer is also a general method. The only physics-related element is the external loss from WMReward. It is unclear why the method is presented as a solution to physical hallucination rather than as a general sampler. If considered as a general sampler, the comparison coverage and novelty may be further limited.
-
The experimental results are not very convincing. Many existing methods are missing in the comparisons. Also the method relies on WMReward loss, but only shows a marginal gain over it. Visual quality, diversity and compute cost are not reported.
-
Section 3.4’s intention is unclear. This may be a writing issue as it is hard to understand.
-
(Minor) There are some sentences that read kind of AI-flavoured.
Questions for authors
The authors can respond to my comments above.