{"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/marvel-40m-multi-level-visual-elaboration-for","title":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","arxiv_id":"2411.17945","date":"2024-11-26","proceeding":"CVPR 2025 1","authors":["Sankalp Sinha","Mohammad Sadil Khan","Muhammad Usama","Shino Sam","Didier Stricker","Sk Aziz Ali","Muhammad Zeshan Afzal"],"abstract":"Generating high-fidelity 3D content from text prompts remains a significant challenge in computer vision due to the limited size, diversity, and annotation depth of the existing datasets. To address this, we introduce MARVEL-40M+, an extensive dataset with 40 million text annotations for over 8.9 million 3D assets aggregated from seven major 3D datasets. Our contribution is a novel multi-stage annotation pipeline that integrates open-source pretrained multi-view VLMs and LLMs to automatically produce multi-level descriptions, ranging from detailed (150-200 words) to concise semantic tags (10-20 words). This structure supports both fine-grained 3D reconstruction and rapid prototyping. Furthermore, we incorporate human metadata from source datasets into our annotation pipeline to add domain-specific information in our annotation and reduce VLM hallucinations. Additionally, we develop MARVEL-FX3D, a two-stage text-to-3D pipeline. We fine-tune Stable Diffusion with our annotations and use a pretrained image-to-3D network to generate 3D textured meshes within 15s. Extensive evaluations show that MARVEL-40M+ significantly outperforms existing datasets in annotation quality and linguistic diversity, achieving win rates of 72.41% by GPT-4 and 73.40% by human evaluators. Project page is available at https://sankalpsinha-cmos.github.io/MARVEL/.","url_abs":"https://arxiv.org/abs/2411.17945v2","url_pdf":"https://arxiv.org/pdf/2411.17945v2.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":"marvel-40m-multi-level-visual-elaboration-for","repo_url":"https://github.com/SadilKhan/MARVEL-FX3D","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"marvel-40m-multi-level-visual-elaboration-for","repo_url":"https://huggingface.co/datasets/sankalpsinha77/MARVEL-40M","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-object-captioning","task_name":"3D Object Captioning"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-dense-captioning","task_name":"3D dense captioning"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-to-3d","task_name":"Image to 3D"},{"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":"gpt-4","method_name":"GPT-4"},{"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":"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":{"syntology_url":"https://syntology.ai/paper/2411.17945","atlas_url":"https://app.syntology.ai/?focus=2411.17945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17945"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/SadilKhan/MARVEL-FX3D","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://huggingface.co/datasets/sankalpsinha77/MARVEL-40M","reach":null}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"c2d989e38cdb2be9","entry":"build_model","repo":"SadilKhan/MARVEL-FX3D","repo_kind":"official","path":"pipeline/dis_image_background_removal.py","file_url":"https://github.com/SadilKhan/MARVEL-FX3D/blob/HEAD/pipeline/dis_image_background_removal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2d989e38cdb2be9"}},{"code_sha256_prefix":"f3aeb0585dbdedf2","entry":"generate_image","repo":"SadilKhan/MARVEL-FX3D","repo_kind":"official","path":"pipeline/imagegen.py","file_url":"https://github.com/SadilKhan/MARVEL-FX3D/blob/HEAD/pipeline/imagegen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3aeb0585dbdedf2"}},{"code_sha256_prefix":"c9897b766a99d6f2","entry":"import_model_class_from_model_name_or_path","repo":"SadilKhan/MARVEL-FX3D","repo_kind":"official","path":"src/fine_tuning/lora_sd3.py","file_url":"https://github.com/SadilKhan/MARVEL-FX3D/blob/HEAD/src/fine_tuning/lora_sd3.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9897b766a99d6f2"}},{"code_sha256_prefix":"cc8d291ad35ef525","entry":"load_text_encoders","repo":"SadilKhan/MARVEL-FX3D","repo_kind":"official","path":"src/fine_tuning/lora_sd3.py","file_url":"https://github.com/SadilKhan/MARVEL-FX3D/blob/HEAD/src/fine_tuning/lora_sd3.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc8d291ad35ef525"}},{"code_sha256_prefix":"5d92a0a218f30ecd","entry":"log_validation","repo":"SadilKhan/MARVEL-FX3D","repo_kind":"official","path":"src/fine_tuning/lora_sd3.py","file_url":"https://github.com/SadilKhan/MARVEL-FX3D/blob/HEAD/src/fine_tuning/lora_sd3.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d92a0a218f30ecd"}},{"code_sha256_prefix":"39a8366aae87acec","entry":"predict","repo":"SadilKhan/MARVEL-FX3D","repo_kind":"official","path":"pipeline/dis_image_background_removal.py","file_url":"https://github.com/SadilKhan/MARVEL-FX3D/blob/HEAD/pipeline/dis_image_background_removal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39a8366aae87acec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}