SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.13271 · 2023

Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 18 functions out of this paper's own repositories and ran 11 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
junwuzhang19/repaint123 canonical 11 of 18
FunctionStatusWhere it lives
build_transform Ran junwuzhang19/repaint123/main2.py
code served (permissive licence) · get_code("57e95166ade5f25c")
dynamic_preprocess Ran junwuzhang19/repaint123/main2.py
code served (permissive licence) · get_code("d610b5eabe0c9db1")
find_closest_aspect_ratio Ran junwuzhang19/repaint123/main2.py
code served (permissive licence) · get_code("bd77f5f8067f18e9")
get_expon_lr_func Ran junwuzhang19/repaint123/gs_renderer.py
code served (permissive licence) · get_code("6d2c15014d993b0e")
inverse_sigmoid Ran junwuzhang19/repaint123/gs_renderer.py
code served (permissive licence) · get_code("b488da571728b636")
numpy_to_torch Ran junwuzhang19/repaint123/metric_utils.py
code served (permissive licence) · get_code("c999c85b86b93312")
optimize_stage_1 Ran junwuzhang19/repaint123/gradio_app.py
code served (permissive licence) · get_code("45a2b5251ba4d0ef")
optimize_stage_2 Ran junwuzhang19/repaint123/gradio_app.py
code served (permissive licence) · get_code("ea1786674cbb3dca")
safe_normalize Ran junwuzhang19/repaint123/mesh.py
code served (permissive licence) · get_code("fe9e0158ece7e066")
score_from_method_for_dataset Ran junwuzhang19/repaint123/metric_utils.py
code served (permissive licence) · get_code("2dfc991848acce36")
strip_lowerdiag Ran junwuzhang19/repaint123/gs_renderer.py
code served (permissive licence) · get_code("cd789cab1b072db4")
dot Not yet run junwuzhang19/repaint123/cam_utils.py
code served (permissive licence) · get_code("e35aafbf0069edb6")
length Not yet run junwuzhang19/repaint123/cam_utils.py
code served (permissive licence) · get_code("43cdc168f88caf9b")
poisson_mesh_reconstruction Not yet run junwuzhang19/repaint123/mesh_utils.py
code served (permissive licence) · get_code("b7f0e912438abda8")
safe_normalize Not yet run junwuzhang19/repaint123/cam_utils.py
code served (permissive licence) · get_code("8a8484ccf552d87f")
scale_img_hwc Not yet run junwuzhang19/repaint123/mesh_renderer.py
code served (permissive licence) · get_code("1eb01adb2d4db29c")
scale_img_nhw Not yet run junwuzhang19/repaint123/mesh_renderer.py
code served (permissive licence) · get_code("7d11ee5002c743ed")
scale_img_nhwc Not yet run junwuzhang19/repaint123/mesh_renderer.py
code served (permissive licence) · get_code("e3e7b5863ff869ea")

Repositories linked to this paper

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

Abstract

Recent one image to 3D generation methods commonly adopt Score Distillation Sampling (SDS). Despite the impressive results, there are multiple deficiencies including multi-view inconsistency, over-saturated and over-smoothed textures, as well as the slow generation speed. To address these deficiencies, we present Repaint123 to alleviate multi-view bias as well as texture degradation and speed up the generation process. The core idea is to combine the powerful image generation capability of the 2D diffusion model and the texture alignment ability of the repainting strategy for generating high-quality multi-view images with consistency. We further propose visibility-aware adaptive repainting strength for overlap regions to enhance the generated image quality in the repainting process. The generated high-quality and multi-view consistent images enable the use of simple Mean Square Error (MSE) loss for fast 3D content generation. We conduct extensive experiments and show that our method has a superior ability to generate high-quality 3D content with multi-view consistency and fine textures in 2 minutes from scratch. Our project page is available at https://pku-yuangroup.github.io/repaint123/.

For agents

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

get_harvested_code_for_paper("2312.13271")
get_code_for_paper("2312.13271")
have("2312.13271")

Connect an agent — have() is free.