SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.08313 · 2019

Unsupervised Sketch-to-Photo Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches pwc_unofficial 9 of 11
FunctionStatusWhere it lives
binary Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/depthestimate/BatchFetcher.py
code served (permissive licence) · get_code("2c9fb04fc48a5a74")
get_norm_layer Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/sketchstd/models/networks.py
code served (permissive licence) · get_code("b27dffc0609fbec0")
get_scheduler Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/sketchstd/models/networks.py
code served (permissive licence) · get_code("f28f371ac79d4e8a")
heatmap Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/depthestimate/visualizeptexample.v.py
code served (permissive licence) · get_code("f4f8efe70b76b9b4")
init_net Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/sketchstd/models/networks.py
code served (permissive licence) · get_code("bf329cef80ee24c5")
mls_affine_deformation Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/sketchstd/img_utils.py
code served (permissive licence) · get_code("28f5dea7ad7deca1")
mls_affine_deformation_1pt Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/sketchstd/img_utils.py
code served (permissive licence) · get_code("362739607d36b783")
rgb2gray Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/depthestimate/BatchFetcher.py
code served (permissive licence) · get_code("eb7801586aa2560a")
rgba2rgb Ran samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/depthestimate/BatchFetcher.py
code served (permissive licence) · get_code("eaa69b40ef46f8c4")
mls_affine_deformation_inv Not yet run samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/sketchstd/img_utils.py
code served (permissive licence) · get_code("96ae243e2e93aeb5")
showpoints Not yet run samaonline/3D-Shape-Reconstruction-from-Free-Hand-Sketches/depthestimate/show3d.py
code served (permissive licence) · get_code("cc0e2a063a44e5cf")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Humans can envision a realistic photo given a free-hand sketch that is not only spatially imprecise and geometrically distorted but also without colors and visual details. We study unsupervised sketch-to-photo synthesis for the first time, learning from unpaired sketch-photo data where the target photo for a sketch is unknown during training. Existing works only deal with style change or spatial deformation alone, synthesizing photos from edge-aligned line drawings or transforming shapes within the same modality, e.g., color images. Our key insight is to decompose unsupervised sketch-to-photo synthesis into a two-stage translation task: First shape translation from sketches to grayscale photos and then content enrichment from grayscale to color photos. We also incorporate a self-supervised denoising objective and an attention module to handle abstraction and style variations that are inherent and specific to sketches. Our synthesis is sketch-faithful and photo-realistic to enable sketch-based image retrieval in practice. An exciting corollary product is a universal and promising sketch generator that captures human visual perception beyond the edge map of a photo.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1909.08313")
get_code_for_paper("1909.08313")
have("1909.08313")

Connect an agent — have() is free.