Mesh Saliency: An Independent Perceptual Measure or A Derivative of Image Saliency?

Ran Song, Wei Zhao, Yitian Zhao, YONGHUAI LIU, Paul Rosin

Research output: Contribution to journalConference proceeding article (ISSN)peer-review

144 Downloads (Pure)


While mesh saliency aims to predict regional importance of 3D surfaces in agreement with human visual perception and is well researched in computer vision and graphics, latest work with eye-tracking experiments shows that state-ofthe-art mesh saliency methods remain poor at predicting human fixations. Cues emerging prominently from these experiments suggest that mesh saliency might associate with the saliency of 2D natural images. This paper proposes a novel deep neural network for learning mesh saliency using image saliency ground truth to 1) investigate whether mesh saliency is an independent perceptual measure or just a derivative of image saliency and 2) provide a weakly supervised method for more accurately predicting mesh saliency.
Through extensive experiments, we not only demonstrate that our method outperforms the current state-of-the-art mesh saliency method by 116% and 21% in terms of linear correlation coefficient and AUC respectively, but also reveal that mesh saliency is intrinsically related with both image saliency and object categorical information. Codes are available at
Original languageEnglish
JournalProceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publication statusAccepted/In press - 3 Mar 2021
EventIEEE/CVF Conference on Computer Vision and Pattern Recognition - Virtual
Duration: 19 Jun 202125 Jun 2021


  • mesh saliency

Research Centres

  • Data & Complex Systems Research Centre
  • Data Science STEM Research Centre

Research Groups

  • Visual Computing Lab


Dive into the research topics of 'Mesh Saliency: An Independent Perceptual Measure or A Derivative of Image Saliency?'. Together they form a unique fingerprint.

Cite this