From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918125033750528 |
|---|---|
| author | Hernández-Cámara, Pablo Malo, Jesus Laparra, Valero |
| author_facet | Hernández-Cámara, Pablo Malo, Jesus Laparra, Valero |
| contents | A number of scientists suggested that human visual perception may emerge from image statistics, shaping efficient neural representations in early vision. In this work, a bio-inspired architecture that can accommodate several known facts in the retina-V1 cortex, the PerceptNet, has been end-to-end optimized for different tasks related to image reconstruction: autoencoding, denoising, deblurring, and sparsity regularization. Our results show that the encoder stage (V1-like layer) consistently exhibits the highest correlation with human perceptual judgments on image distortion despite not using perceptual information in the initialization or training. This alignment exhibits an optimum for moderate noise, blur and sparsity. These findings suggest that the visual system may be tuned to remove those particular levels of distortion with that level of sparsity and that biologically inspired models can learn perceptual metrics without human supervision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10450 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images Hernández-Cámara, Pablo Malo, Jesus Laparra, Valero Computer Vision and Pattern Recognition A number of scientists suggested that human visual perception may emerge from image statistics, shaping efficient neural representations in early vision. In this work, a bio-inspired architecture that can accommodate several known facts in the retina-V1 cortex, the PerceptNet, has been end-to-end optimized for different tasks related to image reconstruction: autoencoding, denoising, deblurring, and sparsity regularization. Our results show that the encoder stage (V1-like layer) consistently exhibits the highest correlation with human perceptual judgments on image distortion despite not using perceptual information in the initialization or training. This alignment exhibits an optimum for moderate noise, blur and sparsity. These findings suggest that the visual system may be tuned to remove those particular levels of distortion with that level of sparsity and that biologically inspired models can learn perceptual metrics without human supervision. |
| title | From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.10450 |