Papers › Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning

Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning

3 Jan 2022ICCV 2023 1arXiv:2201.00785archive 2025-07-28

Siming Yan, Zhenpei Yang, Haoxiang Li, Chen Song, Li Guan, Hao Kang, Gang Hua, QiXing Huang

This paper advocates the use of implicit surface representation in autoencoder-based self-supervised 3D representation learning. The most popular and accessible 3D representation, i.e., point clouds, involves discrete samples of the underlying continuous 3D surface. This discretization process introduces sampling variations on the 3D shape, making it challenging to develop transferable knowledge of the true 3D geometry. In the standard autoencoding paradigm, the encoder is compelled to encode not only the 3D geometry but also information on the specific discrete sampling of the 3D shape into the latent code. This is because the point cloud reconstructed by the decoder is considered unacceptable unless there is a perfect mapping between the original and the reconstructed point clouds. This paper introduces the Implicit AutoEncoder (IAE), a simple yet effective method that addresses the sampling variation issue by replacing the commonly-used point-cloud decoder with an implicit decoder. The implicit decoder reconstructs a continuous representation of the 3D shape, independent of the imperfections in the discrete samples. Extensive experiments demonstrate that the proposed IAE achieves state-of-the-art performance across various self-supervised learning benchmarks.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

simingyan/iae officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Point Cloud Classification3D Point Cloud Linear Classification3D geometryDecoderInductive BiasRepresentation LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40 IAE + DGCNN Mean Accuracy 91.6 #17 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 IAE + DGCNN Overall Accuracy 94.2 #17 of 111 Archive leaderboard report
3D Point Cloud Linear Classification ModelNet40 IAE (DGCNN) Overall Accuracy 92.1 #6 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections