SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.11042 · 2022

Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 5 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
google/hi-lassie pwc_unofficial 5 of 7
FunctionStatusWhere it lives
attn_cosine_sim Ran google/hi-lassie/networks/extractor.py
code served (permissive licence) · get_code("08eeaeb47623cd45")
bfs Ran google/hi-lassie/main/extract_skeleton.py
code served (permissive licence) · get_code("135f37701edf71c1")
get_max_connected_component Ran google/hi-lassie/main/extract_skeleton.py
code served (permissive licence) · get_code("107c3f398275bf2c")
process_bbox Ran google/hi-lassie/utils/data_utils.py
code served (permissive licence) · get_code("461ed6e2762e4454")
sil_loss Ran google/hi-lassie/utils/losses.py
code served (permissive licence) · get_code("17df2c88d2380a00")
find_symmetric_pairs Not yet run google/hi-lassie/main/extract_skeleton.py
code served (permissive licence) · get_code("5be6e9126dc4be51")
part_center_loss Not yet run google/hi-lassie/utils/losses.py
code served (permissive licence) · get_code("7607686657827741")

Repositories linked to this paper

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

Abstract

Automatically estimating 3D skeleton, shape, camera viewpoints, and part articulation from sparse in-the-wild image ensembles is a severely under-constrained and challenging problem. Most prior methods rely on large-scale image datasets, dense temporal correspondence, or human annotations like camera pose, 2D keypoints, and shape templates. We propose Hi-LASSIE, which performs 3D articulated reconstruction from only 20-30 online images in the wild without any user-defined shape or skeleton templates. We follow the recent work of LASSIE that tackles a similar problem setting and make two significant advances. First, instead of relying on a manually annotated 3D skeleton, we automatically estimate a class-specific skeleton from the selected reference image. Second, we improve the shape reconstructions with novel instance-specific optimization strategies that allow reconstructions to faithful fit on each instance while preserving the class-specific priors learned across all images. Experiments on in-the-wild image ensembles show that Hi-LASSIE obtains higher fidelity state-of-the-art 3D reconstructions despite requiring minimum user input.

For agents

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

get_harvested_code_for_paper("2212.11042")
get_code_for_paper("2212.11042")
have("2212.11042")

Connect an agent — have() is free.