{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dit-3d-exploring-plain-diffusion-transformers-1","title":"DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation","arxiv_id":"2307.01831","date":"2023-07-04","proceeding":"NeurIPS 2023 11","authors":["Shentong Mo","Enze Xie","Ruihang Chu","Lewei Yao","Lanqing Hong","Matthias Nießner","Zhenguo Li"],"abstract":"Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape generation, as previous 3D diffusion methods mostly adopted the U-Net architecture. To bridge this gap, we propose a novel Diffusion Transformer for 3D shape generation, namely DiT-3D, which can directly operate the denoising process on voxelized point clouds using plain Transformers. Compared to existing U-Net approaches, our DiT-3D is more scalable in model size and produces much higher quality generations. Specifically, the DiT-3D adopts the design philosophy of DiT but modifies it by incorporating 3D positional and patch embeddings to adaptively aggregate input from voxelized point clouds. To reduce the computational cost of self-attention in 3D shape generation, we incorporate 3D window attention into Transformer blocks, as the increased 3D token length resulting from the additional dimension of voxels can lead to high computation. Finally, linear and devoxelization layers are used to predict the denoised point clouds. In addition, our transformer architecture supports efficient fine-tuning from 2D to 3D, where the pre-trained DiT-2D checkpoint on ImageNet can significantly improve DiT-3D on ShapeNet. Experimental results on the ShapeNet dataset demonstrate that the proposed DiT-3D achieves state-of-the-art performance in high-fidelity and diverse 3D point cloud generation. In particular, our DiT-3D decreases the 1-Nearest Neighbor Accuracy of the state-of-the-art method by 4.59 and increases the Coverage metric by 3.51 when evaluated on Chamfer Distance.","url_abs":"https://arxiv.org/abs/2307.01831v1","url_pdf":"https://arxiv.org/pdf/2307.01831v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dit-3d-exploring-plain-diffusion-transformers-1","repo_url":"https://github.com/DiT-3D/DiT-3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"philosophy","task_name":"Philosophy"},{"task_slug":"point-cloud-generation","task_name":"Point Cloud Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-generation-on-shapenet-airplane","task":"Point Cloud Generation","dataset":"ShapeNet Airplane","model":"DiT-3D","rank_in_archive_order":2,"of":5,"metrics":{"1-NNA-CD":"62.35","CD":"53.16","EMD":"54.39"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-generation-on-shapenet-car","task":"Point Cloud Generation","dataset":"ShapeNet Car","model":"DiT-3D","rank_in_archive_order":1,"of":5,"metrics":{"1-NNA-CD":"51.04","CD":"56.15","EMD":"50.86"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-generation-on-shapenet-chair","task":"Point Cloud Generation","dataset":"ShapeNet Chair","model":"DiT-3D","rank_in_archive_order":1,"of":5,"metrics":{"1-NNA-CD":"51.99","CD":"54.76","EMD":"57.37"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.01831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01831"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DiT-3D/DiT-3D","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"a4339312e5467413","entry":"get_3d_sincos_pos_embed","repo":"DiT-3D/DiT-3D","repo_kind":"listed","path":"models/dit3d.py","file_url":"https://github.com/DiT-3D/DiT-3D/blob/HEAD/models/dit3d.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4339312e5467413"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"03310bba324ae4fb"}},{"code_sha256_prefix":"296657bd96abcae6","entry":"get_3d_sincos_pos_embed_from_grid","repo":"DiT-3D/DiT-3D","repo_kind":"listed","path":"models/dit3d.py","file_url":"https://github.com/DiT-3D/DiT-3D/blob/HEAD/models/dit3d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"296657bd96abcae6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}