- Rating
- 2
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper proposes UniMAC, a unified framework for multi-modal auxiliary learned image compression. It enables a single shared-weight model to leverage diverse auxiliary modalities without separate codecs per scenario. The framework includes modality-specific input adaptation, shared multi-scale auxiliary extraction, auxiliary-conditioned compression, and a unified training strategy. Experiments across five multi-sensor scenarios show consistent rate-distortion improvements over baselines.
Critical strengths
-
The proposed UniMAC accommodates multiple heterogeneous auxiliary modalities using a single shared codec, which is a meaningful direction for multi-sensor systems.
-
The proposed UniMAC introduces modality-specific input adaptation, shared multi-scale auxiliary extraction, auxiliary-conditioned compression, and a unified multi-modal training strategy to effectively exploit heterogeneous multi-modal information.
Critical weaknesses
-
The proposed UniMAC still relies on manually designed modality-specific stems and preprocessing pipelines. When introducing a new modality, explicit engineering is still required rather than direct plug-and-play generalization. Therefore, calling it "unified" may be imprecise.
-
The paper lacks fine-grained ablation studies on the four core stages of the proposed framework, making it difficult to clearly distinguish the individual contribution of each stage to the overall performance gains.
-
In real-world scenarios, auxiliary multi-modal information may be imperfect. For example, depth maps captured by consumer-grade sensors are often degraded, low-resolution, or sparse. It remains unclear whether the proposed method can maintain strong generalization and compression performance under such imperfect auxiliary inputs.
-
The proposed framework appears to rely largely on conventional multi-scale and multi-modal feature fusion strategies. Its key methodological novelty and the distinction from existing fusion-based approaches should be further clarified.
-
The rationale for using gated fusion in the first three stages and cross-attention only in the fourth stage (Eqs. 6–7) is unclear. This design should be better justified, and whether cross-attention at earlier stages could further improve performance is worth investigating.
-
The comparison with only three competing methods is insufficient to fully demonstrate the effectiveness of UniMAC. Moreover, the qualitative results lack visual comparisons with existing methods.
Questions for authors
please see Weaknesses