{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T05:06:39Z","timestamp":1784005599862,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"name":"the Fundamental Research Funds for the Central Universities"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3706293","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:42:29Z","timestamp":1782762149000},"page":"7261-7276","source":"Crossref","is-referenced-by-count":0,"title":["AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3770-7622","authenticated-orcid":false,"given":"Yixuan","family":"Li","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1358-0356","authenticated-orcid":false,"given":"Feng","family":"Tian","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanyan","family":"Guan","sequence":"additional","affiliation":[{"name":"Vivo Mobile Communication Company Ltd., Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhao","family":"Ge","sequence":"additional","affiliation":[{"name":"Vivo Mobile Communication Company Ltd., Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Vivo Mobile Communication Company Ltd., Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-8965","authenticated-orcid":false,"given":"Yichao","family":"Yan","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-2845","authenticated-orcid":false,"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"LRM: Large reconstruction model for single image to 3D","volume-title":"Proc. ICLR","author":"Hong"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref4","first-page":"1","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. ICLR","author":"Poole"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref6","article-title":"TripoSR: Fast 3D object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"arXiv:2403.02151"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref9","first-page":"1","article-title":"Text-to-3D with classifier score distillation","volume-title":"Proc. ICLR","author":"Yu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. ICLR","author":"Podell"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00863"},{"key":"ref21","first-page":"1","article-title":"HIFA: High-fidelity text-to-3D generation with advanced diffusion guidance","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0523"},{"key":"ref23","article-title":"Re-imagine the negative prompt algorithm: Transform 2D diffusion into 3D, alleviate Janus problem and beyond","author":"Armandpour","year":"2023","journal-title":"arXiv:2304.04968"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00513"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00974"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_25"},{"key":"ref27","first-page":"1","article-title":"RecDreamer: Consistent text-to-3D generation via uniform score distillation","volume-title":"Proc. ICLR","author":"Zheng"},{"key":"ref28","first-page":"1","article-title":"MVDream: Multi-view diffusion for 3D generation","volume-title":"Proc. ICLR","author":"Shi"},{"key":"ref29","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref31","first-page":"1","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref32","first-page":"1","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. ICML","author":"Sohl-Dickstein"},{"key":"ref33","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Song"},{"key":"ref34","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref35","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv:2212.08751"},{"key":"ref36","first-page":"7220","article-title":"PolyGen: An autoregressive generative model of 3D meshes","volume-title":"Proc. ICML","author":"Nash"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535389"},{"key":"ref41","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref44","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref46","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02298-y"},{"key":"ref49","first-page":"1","article-title":"DreamGaussian: Generative Gaussian splatting for efficient 3D content creation","volume-title":"Proc. ICLR","author":"Tang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_8"},{"key":"ref52","article-title":"Consistent flow distillation for text-to-3D generation","author":"Yan","year":"2025","journal-title":"arXiv:2501.05445"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref54","article-title":"Zero123++: A single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv:2310.15110"},{"key":"ref55","first-page":"1","article-title":"SyncDreamer: Generating multiview-consistent images from a single-view image","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref56","first-page":"1","article-title":"Magic123: One image to high-quality 3D object generation using both 2D and 3D diffusion priors","volume-title":"Proc. ICLR","author":"Qian"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_15"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0919-5_26"},{"key":"ref59","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref60","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_1"},{"key":"ref62","article-title":"Grounded compositional and diverse text-to-3D with pretrained multi-view diffusion model","author":"Li","year":"2024","journal-title":"arXiv:2404.18065"},{"key":"ref63","article-title":"$\\text{T}^{3}$\nbench: Benchmarking current progress in text-to-3D generation","author":"He","year":"2023","journal-title":"arXiv:2310.02977"},{"key":"ref64","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NIPS","author":"Heusel"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"ref67","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref68","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref69","article-title":"Threestudio: A unified framework for 3D content generation","author":"Guo","year":"2023"},{"key":"ref70","article-title":"Hunyuan3D 2.0: Scaling diffusion models for high resolution textured 3D assets generation","author":"Zhao","year":"2025","journal-title":"arXiv:2501.12202"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11585937.pdf?arnumber=11585937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T04:42:51Z","timestamp":1784004171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11585937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3706293","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}