Papers › Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models

Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models

27 Jul 2023ICCV 2023 1arXiv:2307.14971archive 2025-07-28

Ziyi Wang, Xumin Yu, Yongming Rao, Jie zhou, Jiwen Lu

With the overwhelming trend of mask image modeling led by MAE, generative pre-training has shown a remarkable potential to boost the performance of fundamental models in 2D vision. However, in 3D vision, the over-reliance on Transformer-based backbones and the unordered nature of point clouds have restricted the further development of generative pre-training. In this paper, we propose a novel 3D-to-2D generative pre-training method that is adaptable to any point cloud model. We propose to generate view images from different instructed poses via the cross-attention mechanism as the pre-training scheme. Generating view images has more precise supervision than its point cloud counterpart, thus assisting 3D backbones to have a finer comprehension of the geometrical structure and stereoscopic relations of the point cloud. Experimental results have proved the superiority of our proposed 3D-to-2D generative pre-training over previous pre-training methods. Our method is also effective in boosting the performance of architecture-oriented approaches, achieving state-of-the-art performance when fine-tuning on ScanObjectNN classification and ShapeNetPart segmentation tasks. Code is available at https://github.com/wangzy22/TAP.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its page in Syntology's graph, with its repositories and citations.

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

Code

wangzy22/tap 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 Part Segmentation3D Point Cloud Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part PointMLP+TAP Class Average IoU 85.2 #9 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointMLP+TAP Instance Average IoU 86.9 #9 of 67 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointMLP+TAP Overall Accuracy 88.5 #36 of 77 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.

Methods

MAE

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