{"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/enhancing-motion-in-text-to-video-generation","title":"Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning","arxiv_id":"2410.24219","date":"2024-10-31","proceeding":null,"authors":["Penghui Ruan","Pichao Wang","Divya Saxena","Jiannong Cao","Yuhui Shi"],"abstract":"Despite advancements in Text-to-Video (T2V) generation, producing videos with realistic motion remains challenging. Current models often yield static or minimally dynamic outputs, failing to capture complex motions described by text. This issue stems from the internal biases in text encoding, which overlooks motions, and inadequate conditioning mechanisms in T2V generation models. To address this, we propose a novel framework called DEcomposed MOtion (DEMO), which enhances motion synthesis in T2V generation by decomposing both text encoding and conditioning into content and motion components. Our method includes a content encoder for static elements and a motion encoder for temporal dynamics, alongside separate content and motion conditioning mechanisms. Crucially, we introduce text-motion and video-motion supervision to improve the model's understanding and generation of motion. Evaluations on benchmarks such as MSR-VTT, UCF-101, WebVid-10M, EvalCrafter, and VBench demonstrate DEMO's superior ability to produce videos with enhanced motion dynamics while maintaining high visual quality. Our approach significantly advances T2V generation by integrating comprehensive motion understanding directly from textual descriptions. Project page: https://PR-Ryan.github.io/DEMO-project/","url_abs":"https://arxiv.org/abs/2410.24219v1","url_pdf":"https://arxiv.org/pdf/2410.24219v1.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":"enhancing-motion-in-text-to-video-generation","repo_url":"https://github.com/pr-ryan/demo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.24219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24219"}},"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/pr-ryan/demo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"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":"b64e0147e4a1f775","entry":"assign_prior_mudule_cfg","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/assign_cfg.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/assign_cfg.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":"b64e0147e4a1f775"}},{"code_sha256_prefix":"ccc751f51ec26e45","entry":"assign_signle_cfg","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/assign_cfg.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/assign_cfg.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":"ccc751f51ec26e45"}},{"code_sha256_prefix":"bb7489dd987a9149","entry":"assign_vldm_vsr_mudule_cfg","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/assign_cfg.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/assign_cfg.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":"bb7489dd987a9149"}},{"code_sha256_prefix":"ba13909bd366ecb0","entry":"build_from_config","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/registry.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/registry.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":"ba13909bd366ecb0"}},{"code_sha256_prefix":"e12405fa6be0a921","entry":"build_func","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/registry_class.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/registry_class.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":"e12405fa6be0a921"}},{"code_sha256_prefix":"9b3aac7a14d2a719","entry":"gen_text_image","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/video_op.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/video_op.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":"9b3aac7a14d2a719"}},{"code_sha256_prefix":"b6d6bcb982b768cc","entry":"get_logger","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/logging.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/logging.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":"b6d6bcb982b768cc"}},{"code_sha256_prefix":"1d504697143a06b9","entry":"get_rank","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/distributed.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/distributed.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":"1d504697143a06b9"}},{"code_sha256_prefix":"151fc386a67a4f69","entry":"get_world_size","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/distributed.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/distributed.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":"151fc386a67a4f69"}},{"code_sha256_prefix":"69723155a0580292","entry":"new_group","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/distributed.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/distributed.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":"69723155a0580292"}},{"code_sha256_prefix":"2c9668e7429db7c5","entry":"to_device","repo":"pr-ryan/demo","repo_kind":"official","path":"utils/util.py","file_url":"https://github.com/pr-ryan/demo/blob/HEAD/utils/util.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":"2c9668e7429db7c5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}