{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/exploiting-gan-internal-capacity-for-high","title":"Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images","arxiv_id":"1911.05630","date":"2019-10-26","proceeding":null,"authors":["Marcos Pividori","Guillermo L. Grinblat","Lucas C. Uzal"],"abstract":"Generative Adversarial Networks (GAN) have demonstrated impressive results in modeling the distribution of natural images, learning latent representations that capture semantic variations in an unsupervised basis. Beyond the generation of novel samples, it is of special interest to exploit the ability of the GAN generator to model the natural image manifold and hence generate credible changes when manipulating images. However, this line of work is conditioned by the quality of the reconstruction. Until now, only inversion to the latent space has been considered, we propose to exploit the representation in intermediate layers of the generator, and we show that this leads to increased capacity. In particular, we observe that the representation after the first dense layer, present in all state-of-the-art GAN models, is expressive enough to represent natural images with high visual fidelity. It is possible to interpolate around these images obtaining a sequence of new plausible synthetic images that cannot be generated from the latent space. Finally, as an example of potential applications that arise from this inversion mechanism, we show preliminary results in exploiting the learned representation in the attention map of the generator to obtain an unsupervised segmentation of natural images.","url_abs":"https://arxiv.org/abs/1911.05630v1","url_pdf":"https://arxiv.org/pdf/1911.05630v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploiting-gan-internal-capacity-for-high","repo_url":"https://github.com/CIFASIS/exploiting-gan-internal-capacity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1911.05630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.05630"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CIFASIS/exploiting-gan-internal-capacity","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b3acc4409b6bce61","entry":"interpolate","repo":"CIFASIS/exploiting-gan-internal-capacity","repo_kind":"official","path":"interpolation.py","file_url":"https://github.com/CIFASIS/exploiting-gan-internal-capacity/blob/HEAD/interpolation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3acc4409b6bce61"}},{"code_sha256_prefix":"36bc4cbab4bc2b1e","entry":"one_hot","repo":"CIFASIS/exploiting-gan-internal-capacity","repo_kind":"official","path":"inversion.py","file_url":"https://github.com/CIFASIS/exploiting-gan-internal-capacity/blob/HEAD/inversion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36bc4cbab4bc2b1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}