{"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/director3d-real-world-camera-trajectory-and","title":"Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text","arxiv_id":"2406.17601","date":"2024-06-25","proceeding":null,"authors":["Xinyang Li","Zhangyu Lai","Linning Xu","Yansong Qu","Liujuan Cao","Shengchuan Zhang","Bo Dai","Rongrong Ji"],"abstract":"Recent advancements in 3D generation have leveraged synthetic datasets with ground truth 3D assets and predefined cameras. However, the potential of adopting real-world datasets, which can produce significantly more realistic 3D scenes, remains largely unexplored. In this work, we delve into the key challenge of the complex and scene-specific camera trajectories found in real-world captures. We introduce Director3D, a robust open-world text-to-3D generation framework, designed to generate both real-world 3D scenes and adaptive camera trajectories. To achieve this, (1) we first utilize a Trajectory Diffusion Transformer, acting as the Cinematographer, to model the distribution of camera trajectories based on textual descriptions. (2) Next, a Gaussian-driven Multi-view Latent Diffusion Model serves as the Decorator, modeling the image sequence distribution given the camera trajectories and texts. This model, fine-tuned from a 2D diffusion model, directly generates pixel-aligned 3D Gaussians as an immediate 3D scene representation for consistent denoising. (3) Lastly, the 3D Gaussians are refined by a novel SDS++ loss as the Detailer, which incorporates the prior of the 2D diffusion model. Extensive experiments demonstrate that Director3D outperforms existing methods, offering superior performance in real-world 3D generation.","url_abs":"https://arxiv.org/abs/2406.17601v1","url_pdf":"https://arxiv.org/pdf/2406.17601v1.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":"director3d-real-world-camera-trajectory-and","repo_url":"https://github.com/imlixinyang/director3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"scene-generation","task_name":"Scene Generation"},{"task_slug":"text-to-3d","task_name":"Text to 3D"}],"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":"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":"latent-diffusion-model","method_name":"Latent Diffusion Model"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.17601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17601"}},"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/imlixinyang/director3d","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":4,"ran":3,"ran_honours":3,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":15,"ran":11,"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":15,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/vae_hacked.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/vae_hacked.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"c34231087ef1ed71","entry":"build_rotation","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/refiners/gs_utils.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/refiners/gs_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c34231087ef1ed71"}},{"code_sha256_prefix":"293345bd844c518f","entry":"getProjectionMatrix","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/renderers/gaussians_renderer.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/renderers/gaussians_renderer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"293345bd844c518f"}},{"code_sha256_prefix":"c92c27c924b517e8","entry":"get_2d_sincos_pos_embed","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/dit.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/dit.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c92c27c924b517e8"}},{"code_sha256_prefix":"221b2d116fdf1032","entry":"get_obj_from_str","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/unet_hacked.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/unet_hacked.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"221b2d116fdf1032"}},{"code_sha256_prefix":"cb49209c125de1b4","entry":"get_timestep_embedding","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/vae_hacked.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/vae_hacked.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb49209c125de1b4"}},{"code_sha256_prefix":"efa45361a2054e42","entry":"import_str","repo":"imlixinyang/director3d","repo_kind":"official","path":"utils.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"efa45361a2054e42"}},{"code_sha256_prefix":"b488da571728b636","entry":"inverse_sigmoid","repo":"imlixinyang/director3d","repo_kind":"official","path":"utils.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b488da571728b636"}},{"code_sha256_prefix":"c984209a2c66afbe","entry":"make_beta_schedule","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/unet_hacked.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/unet_hacked.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c984209a2c66afbe"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/dit.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/dit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"03310bba324ae4fb"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/vae_hacked.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/vae_hacked.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"665d8a4e8f673a4c","entry":"get_2d_sincos_pos_embed_from_grid","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/dit.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/dit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"665d8a4e8f673a4c"}},{"code_sha256_prefix":"ef52d142b2c30ac2","entry":"instantiate_from_config","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/unet_hacked.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/unet_hacked.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef52d142b2c30ac2"}},{"code_sha256_prefix":"e5e924570703db04","entry":"inverse_softplus","repo":"imlixinyang/director3d","repo_kind":"official","path":"modules/refiners/gs_utils.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/modules/refiners/gs_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e5e924570703db04"}},{"code_sha256_prefix":"f4ca75183697e34c","entry":"matrix_to_square","repo":"imlixinyang/director3d","repo_kind":"official","path":"utils.py","file_url":"https://github.com/imlixinyang/director3d/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f4ca75183697e34c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}