ARTFLOW: A Fast, Biologically Inspired Neural Network that Learns Optic Flow Templates for Self-Motion Estimation

Layton, Oliver W.

doi:10.3390/s21248217

Cited by 8 publications

(7 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, the CD model captures the elevated human bias in the postblackout condition without explicitly modeling expectation ( Figure 6 a). Dynamics that depend on whether the optic flow signal affirms or violates expectations about the heading direction would be compatible with adaptive resonance theory ( Grossberg, 1976 , 2013 ; Brito Da Silva, Elnabarawy, & Wunsch, 2019 ; Layton, 2021 ) and predictive coding ( Friston, 2010 ).…”

Section: Discussionmentioning

confidence: 60%

Temporal stability of human heading perception

2023

Self Cite

View full text Add to dashboard Cite

Humans are capable of accurately judging their heading from optic flow during straight forward self-motion. Despite the global coherence in the optic flow field, however, visual clutter and other naturalistic conditions create constant flux on the eye. This presents a problem that must be overcome to accurately perceive heading from optic flow—the visual system must maintain sensitivity to optic flow variations that correspond with actual changes in self-motion and disregard those that do not. One solution could involve integrating optic flow over time to stabilize heading signals while suppressing transient fluctuations. Stability, however, may come at the cost of sluggishness. Here, we investigate the stability of human heading perception when subjects judge their heading after the simulated direction of self-motion changes. We found that the initial heading exerted an attractive influence on judgments of the final heading. Consistent with an evolving heading representation, bias toward the initial heading increased with the size of the heading change and as the viewing duration of the optic flow consistent with the final heading decreased. Introducing periods of sensory dropout (blackouts) later in the trial increased bias whereas an earlier one did not. Simulations of a neural model, the Competitive Dynamics Model, demonstrates that a mechanism that produces an evolving heading signal through recurrent competitive interactions largely captures the human data. Our findings characterize how the visual system balances stability in heading perception with sensitivity to change and support the hypothesis that heading perception evolves over time.

show abstract

Section: Discussionmentioning

confidence: 60%

Temporal stability of human heading perception

2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…To evaluate the method used in this paper, after 2000 rounds of training, the results generated by this method were compared with ArtFlow [30], ChromaGAN [31], Pix2pix, and UGAN [32]. The comparison results are shown in Figure 6: The following conclusions can be drawn from the information in Figure 6 above.…”

Section: Subjective Evaluationmentioning

confidence: 91%

Digital Inpainting of Mural Images Based on DC-CycleGAN

Zhang

2023

Preprint

View full text Add to dashboard Cite

Located in Dunhuang, northwest China, the Mogao Grottoes are a cultural treasure of China and the world. However, after more than 2,000 years of weathering and destruction, many murals faded and were damaged. This treasure of human art is in danger. Mural inpainting through deep learning can permanently preserve mural information. In order to reduce manpower and material resources, the efficiency of mural image restoration is significantly improved. Therefore, a digital restoration method combining Deformable Convolution (DCN), ECANet, ResNet and Cycle Generative Adversarial Network (CycleGAN) is proposed. We name it DC-CycleGAN. Compared with other image digital inpainting methods, the proposed DC-CycleGAN based mural image color inpainting method has better inpainting effects and higher model performance, which can better capture the high-frequency characteristics of the image and avoid network degradation and gradient disappearance. The digital restoration of mural images provides a new theoretical and scientific basis for the protection and restoration process of murals, and shows the latest attempts of mural restoration.

show abstract

“…To evaluate the method used in this paper, after 10000 rounds of training, the results generated by this method were compared with CycleGAN, ArtFlow [24], Chro-maGAN [25] and UGAN [26]. The comparison results are shown in Fig.…”

Section: Subjective Evaluationmentioning

confidence: 99%

Digital inpainting of mural images based on DC-CycleGAN

Xu,

Zhang,

2023

Herit Sci

View full text Add to dashboard Cite

Located in Dunhuang, northwest China, the Mogao Grottoes are a cultural treasure of China and the world. However, after more than 2000 years of weathering and destruction, many murals faded and were damaged. This treasure of human art is in danger. Mural inpainting through deep learning can permanently preserve mural information. Therefore, a digital restoration method combining the Deformable Convolution (DCN), ECANet, ResNet and Cycle Generative Adversarial Network (CycleGAN) is proposed. We name it DC-CycleGAN. Compared with other image digital inpainting methods, the proposed DC-CycleGAN based mural image color inpainting method has better inpainting effects and higher model performance. Compared with the current repair network, the Frechet Inception Distance (FID) value and the two-image structural similarity metric (SSIM) value are increased by 52.61% and 7.08%, respectively. Image color inpainting of Dunhuang murals can not only protect and inherit Chinese culture, but also promote academic research and development in related fields.

show abstract

ARTFLOW: A Fast, Biologically Inspired Neural Network that Learns Optic Flow Templates for Self-Motion Estimation

Cited by 8 publications

References 54 publications

Temporal stability of human heading perception

Temporal stability of human heading perception

Digital Inpainting of Mural Images Based on DC-CycleGAN

Digital inpainting of mural images based on DC-CycleGAN

Contact Info

Product

Resources

About