Papers › Volumetric and Multi-View CNNs for Object Classification on 3D Data

Volumetric and Multi-View CNNs for Object Classification on 3D Data

12 Apr 2016CVPR 2016 6arXiv:1604.03265archive 2025-07-28

Charles R. Qi, Hao Su, Matthias Niessner, Angela Dai, Mengyuan Yan, Leonidas J. Guibas

3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-the-art methods rely on CNNs to address this problem. Recently, we witness two types of CNNs being developed: CNNs based upon volumetric representations versus CNNs based upon multi-view representations. Empirical results from these two types of CNNs exhibit a large gap, indicating that existing volumetric CNN architectures and approaches are unable to fully exploit the power of 3D representations. In this paper, we aim to improve both volumetric CNNs and multi-view CNNs according to extensive analysis of existing approaches. To this end, we introduce two distinct network architectures of volumetric CNNs. In addition, we examine multi-view CNNs, where we introduce multi-resolution filtering in 3D. Overall, we are able to outperform current state-of-the-art methods for both volumetric CNNs and multi-view CNNs. We provide extensive experiments designed to evaluate underlying design choices, thus providing a better understanding of the space of methods available for object classification on 3D data.

PaperPDFConference PDFCode

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

Code

LONG-9621/3DCNN mentioned on GitHubtorchNOASSERTION report
charlesq34/3dcnn.torch mentioned on GitHubtorchNOASSERTION 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 Object Recognition3D Point Cloud ClassificationGeneral Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Recognition ModelNet40 MVCNN-MultiRes Accuracy 93.8% #3 of 6 Archive leaderboard report
3D Point Cloud Classification ModelNet40 Subvolume Overall Accuracy 89.2 #106 of 111 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