{"url":"/task/text-to-3d","name":"Text to 3D","slug":"text-to-3d","description_markdown":"Task involves generating 3D objects based on the text prompt provided to the system.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":314,"papers_with_code":102,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/text-to-3d-on-t-3-bench","slug":"text-to-3d-on-t-3-bench","dataset":"T$^3$Bench","dataset_url":"/dataset/t-3-bench","rows_in_archive":6,"metrics":["Avg"],"first_row_in_archive_order":{"model":"ProlificDreamer","paper_title":"0/1 Deep Neural Networks via Block Coordinate Descent","paper_url":"/paper/0-1-deep-neural-networks-via-block-coordinate","paper_date":"2022-06-19","arxiv_id":"2206.09379","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/t-3-bench","name":"T$^3$Bench","full_name":"","num_papers_in_archive":8},{"url":"/dataset/text2cad","name":"Text2CAD","full_name":"Text2CAD","num_papers_in_archive":2},{"url":"/dataset/blendnet","name":"BlendNet","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cadbench","name":"CADBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/stabletext2lego","name":"StableText2Lego","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/3d","name":"3D"},{"url":"/task/text-to-image-generation-1","name":"Text to Image Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":102,"tagged_in_all":314,"items":[{"url":"/paper/text-to-image-rectified-flow-as-plug-and-play","title":"Text-to-Image Rectified Flow as Plug-and-Play Priors","date":"2024-06-05","arxiv_id":"2406.03293","repositories_listed":4,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":5}},{"url":"/paper/dreamfusion-text-to-3d-using-2d-diffusion","title":"DreamFusion: Text-to-3D using 2D Diffusion","date":"2022-09-29","arxiv_id":"2209.14988","repositories_listed":4,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/cephalo-multi-modal-vision-language-models","title":"Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design","date":"2024-05-29","arxiv_id":"2405.19076","repositories_listed":3,"syntology":null},{"url":"/paper/fantasia3d-disentangling-geometry-and","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","date":"2023-03-24","arxiv_id":"2303.13873","repositories_listed":3,"syntology":{"n":18,"n_ran":7,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/marvel-40m-multi-level-visual-elaboration-for","title":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","date":"2024-11-26","arxiv_id":"2411.17945","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/view-selection-for-3d-captioning-via","title":"View Selection for 3D Captioning via Diffusion Ranking","date":"2024-04-11","arxiv_id":"2404.07984","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/controllable-text-to-3d-generation-via","title":"Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting","date":"2024-03-15","arxiv_id":"2403.09981","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/geodream-disentangling-2d-and-geometric","title":"GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation","date":"2023-11-29","arxiv_id":"2311.17971","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/syncdreamer-generating-multiview-consistent","title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","date":"2023-09-07","arxiv_id":"2309.03453","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/prolificdreamer-high-fidelity-and-diverse","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","date":"2023-05-25","arxiv_id":"2305.16213","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/make-it-3d-high-fidelity-3d-creation-from-a","title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior","date":"2023-03-24","arxiv_id":"2303.14184","repositories_listed":2,"syntology":null},{"url":"/paper/latent-nerf-for-shape-guided-generation-of-3d","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","date":"2022-11-14","arxiv_id":"2211.07600","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/generating-physically-stable-and-buildable","title":"Generating Physically Stable and Buildable LEGO Designs from Text","date":"2025-05-08","arxiv_id":"2505.05469","repositories_listed":1,"syntology":null},{"url":"/paper/apply-hierarchical-chain-of-generation-to","title":"Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation","date":"2025-05-07","arxiv_id":"2505.05505","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/sort3d-spatial-object-centric-reasoning","title":"SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models","date":"2025-04-25","arxiv_id":"2504.18684","repositories_listed":1,"syntology":null},{"url":"/paper/dimer-disentangled-mesh-reconstruction-model-1","title":"DiMeR: Disentangled Mesh Reconstruction Model","date":"2025-04-24","arxiv_id":"2504.17670","repositories_listed":1,"syntology":null},{"url":"/paper/text-based-animatable-3d-avatars-with","title":"Text-based Animatable 3D Avatars with Morphable Model Alignment","date":"2025-04-22","arxiv_id":"2504.15835","repositories_listed":1,"syntology":{"n":12,"n_ran":4,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/consdreamer-advancing-multi-view-consistency","title":"ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation","date":"2025-04-03","arxiv_id":"2504.02316","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-rendering-distillation-adapting","title":"Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data","date":"2025-03-27","arxiv_id":"2503.21694","repositories_listed":1,"syntology":null},{"url":"/paper/rewardsds-aligning-score-distillation-via","title":"RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling","date":"2025-03-12","arxiv_id":"2503.09601","repositories_listed":1,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/kiss3dgen-repurposing-image-diffusion-models","title":"Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation","date":"2025-03-03","arxiv_id":"2503.01370","repositories_listed":1,"syntology":null},{"url":"/paper/multi-dimensional-quality-assessment-for-text","title":"Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model","date":"2025-02-24","arxiv_id":"2502.16915","repositories_listed":1,"syntology":null},{"url":"/paper/strandhead-text-to-strand-disentangled-3d","title":"StrandHead: Text to Strand-Disentangled 3D Head Avatars Using Hair Geometric Priors","date":"2024-12-16","arxiv_id":"2412.11586","repositories_listed":1,"syntology":null},{"url":"/paper/blenderllm-training-large-language-models-for","title":"BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement","date":"2024-12-16","arxiv_id":"2412.14203","repositories_listed":1,"syntology":null},{"url":"/paper/generate-any-scene-evaluating-and-improving","title":"Generate Any Scene: Evaluating and Improving Text-to-Vision Generation with Scene Graph Programming","date":"2024-12-11","arxiv_id":"2412.08221","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/tactile-dreamfusion-exploiting-tactile","title":"Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation","date":"2024-12-09","arxiv_id":"2412.06785","repositories_listed":1,"syntology":{"n":18,"n_ran":1,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/towards-rich-emotions-in-3d-avatars-a-text-to","title":"Towards Rich Emotions in 3D Avatars: A Text-to-3D Avatar Generation Benchmark","date":"2024-12-03","arxiv_id":"2412.02508","repositories_listed":1,"syntology":null},{"url":"/paper/3d-adapter-geometry-consistent-multi-view","title":"3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation","date":"2024-10-24","arxiv_id":"2410.18974","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/scenecraft-layout-guided-3d-scene-generation","title":"SceneCraft: Layout-Guided 3D Scene Generation","date":"2024-10-11","arxiv_id":"2410.09049","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/dreamwaltz-g-expressive-3d-gaussian-avatars","title":"DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion","date":"2024-09-25","arxiv_id":"2409.17145","repositories_listed":1,"syntology":null}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}