Pith. sign in

REVIEW 11 cited by

Understanding SSIM

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.13846 v2 pith:BUVPRZWL submitted 2020-06-24 eess.IV cs.GR

Jim Nilsson , Tomas Akenine-Möller This is my paper · ORCID
classification eess.IVcs.GR
keywords ssimdeepimageindexqualityresearchscrutinyalmost
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The use of the structural similarity index (SSIM) is widespread. For almost two decades, it has played a major role in image quality assessment in many different research disciplines. Clearly, its merits are indisputable in the research community. However, little deep scrutiny of this index has been performed. Contrary to popular belief, there are some interesting properties of SSIM that merit such scrutiny. In this paper, we analyze the mathematical factors of SSIM and show that it can generate results, in both synthetic and realistic use cases, that are unexpected, sometimes undefined, and nonintuitive. As a consequence, assessing image quality based on SSIM can lead to incorrect conclusions and using SSIM as a loss function for deep learning can guide neural network training in the wrong direction.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoning

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A spiking neural network with subtractive and additive attention performs all-in-one image restoration in one time step, matching older ANN baselines with much lower estimated energy.

  2. Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows

    physics.flu-dyn 2026-07 conditional novelty 6.0 of 10

    A new 2.4 TB benchmark shows no single ML surrogate dominates on shock-driven multiphase flows, and composite losses with SoftAdapt weighting improve interface and spectral fidelity.

  3. 4D Human-Scene Reconstruction from Low-Overlap Captures

    cs.CV 2026-07 conditional novelty 6.0 of 10

    StudioRecon delivers SOTA novel-view synthesis of 4D human scenes from sparse low-overlap cameras by decoupling background densification via video diffusion from SMPL-constrained human Gaussians plus recursive enhancement.

  4. Transformer-based Multisensor Data Fusion of Ultrasonic Guided Wave and FBG-based Strain Measurements for Multitask Aerospace Structural Health Monitoring

    eess.SP 2026-06 conditional novelty 6.0 of 10

    Transformer fusion of asynchronous PZT guided-wave and FBG strain data yields HI MAE/RMSE <0.1 and localization MAE/RMSE <0.0465/0.1571, beating single-sensor and SOTA DNN baselines by ~60% on ReMAP composite fatigue panels.

  5. Mirai: A Wearable Proactive AI "Inner-Voice" for Contextual Nudging

    cs.HC 2025-02 conditional novelty 6.0 of 10

    A wearable AI prototype combines egocentric vision, speech, and voice cloning to deliver proactive first-person nudges for behavior change, with reported end-to-end latency under one second.

  6. QWRF-Net: A Quantum-Wavelet Framework with Rectified Flow for Short-Term Precipitation Nowcasting

    cs.LG 2026-08 conditional novelty 5.0 of 10

    QWRF-Net, a wavelet-quantum-flow nowcasting model, reports modest but consistent gains on KNMI and SEVIR at high precipitation thresholds and extreme events.

  7. CloudBreaker: Breaking the Cloud Covers of Sentinel-2 Images using Multi-Stage Trained Conditional Flow Matching on Sentinel-1

    cs.CV 2025-08 conditional novelty 5.0 of 10

    CloudBreaker trains a multi-stage conditional flow-matching model on paired Sentinel-1 radar and Sentinel-2 optical data to synthesize RGB, NDVI, and NDWI images under cloud cover.

  8. SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design

    cs.CV 2025-06 conditional novelty 5.0 of 10

    SlideCoder converts slide design images to editable python-pptx code and reports large gains over prior baselines on a new difficulty-tiered benchmark.

  9. ClusIR: Towards Cluster-Guided All-in-One Image Restoration

    cs.CV 2025-12 conditional novelty 4.0 of 10

    A cluster-guided mixture-of-experts network with frequency modulation reports competitive all-in-one image restoration results, with uneven gains and no public code.

  10. Beyond Imaging: Vision Transformer Digital Twin Surrogates for 3D+T Biological Tissue Dynamics

    eess.IV 2025-08 conditional novelty 4.0 of 10

    A DINO-pretrained vision transformer with multi-view fusion reconstructs 3D+t stacks of Drosophila midgut tissue, reporting average MSE 9.33 and SSIM 0.87, but its temporal claim is built on independent specimens, not...

  11. Gen-AI Police Sketches with Stable Diffusion

    cs.CV 2025-07 reject novelty 2.0 of 10

    A small empirical study finds that a baseline Stable Diffusion model generates police sketches that score higher on SSIM, PSNR, CLIP score, and LPIPS than versions augmented with CLIP or LoRA-fine-tuned CLIP.

Pith tools