SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.06383 · ICCV · 2023

U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds

Federico Tombari, Didier Stricker, Xiangyang Ji, Yan Di, Chenyangguang Zhang, Ruida Zhang, Fabian Manhardt, Yongzhi Su, Jason Rambach

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 6 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
zhangcyg/u-red — 6 of 14
FunctionStatusWhere it lives
FeedForwardNet_norm Ran zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("384c2193e4e4a98b")
GeneralizedFavorAttention Ran zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("8bddc8c728a762ba")
MultiheadAttention Ran zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("c9afeb7769ae9b17")
get_attention_mechanism Ran zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("b2c4f20e9d6d15a3")
linear_attention Ran zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("e44c028c4b4ffc80")
linear_attention_elu Ran zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("a877505eed6a7d45")
DeformNet_MatchingNet Not yet run zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("4b0f9015b6d03df6")
DescriptorsCrossAttention Not yet run zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("540314b85d9e8c44")
DescriptorsSelfAttention Not yet run zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("446399ca52f6ed68")
FavorAttention Not yet run zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("844393af52f001c5")
GraphAttentionNet Not yet run zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("43809d289d7b133c")
ResidualAttentionMessagePropagation Not yet run zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("4267d6a47c78f546")
SoftmaxFavorAttention Not yet run zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("41c3f8363a9597c3")
softmax_attention Not yet run zhangcyg/u-red/network/deformation_net.py
pointer only (licence: NONE) · get_code("c243e6486ecd3d91")

Repositories linked to this paper

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

Abstract

In this paper, we propose U-RED, an Unsupervised shape REtrieval and Deformation pipeline that takes an arbitrary object observation as input, typically captured by RGB images or scans, and jointly retrieves and deforms the geometrically similar CAD models from a pre-established database to tightly match the target. Considering existing methods typically fail to handle noisy partial observations, U-RED is designed to address this issue from two aspects. First, since one partial shape may correspond to multiple potential full shapes, the retrieval method must allow such an ambiguous one-to-many relationship. Thereby U-RED learns to project all possible full shapes of a partial target onto the surface of a unit sphere. Then during inference, each sampling on the sphere will yield a feasible retrieval. Second, since real-world partial observations usually contain noticeable noise, a reliable learned metric that measures the similarity between shapes is necessary for stable retrieval. In U-RED, we design a novel point-wise residualguided metric that allows noise-robust comparison. Extensive experiments on the synthetic datasets PartNet, Comple-mentMe and the real-world dataset Scan2CAD demonstrate that U-RED surpasses existing state-of-the-art approaches by 47.3%, 16.7% and 31.6% respectively under Chamfer Distance.

For agents

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

get_harvested_code_for_paper("2308.06383")
get_code_for_paper("2308.06383")
have("2308.06383")

Connect an agent — have() is free.