{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:38:10Z","timestamp":1777995490107,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2126407"],"award-info":[{"award-number":["2126407"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730751","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:42:43Z","timestamp":1753260163000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Generative detail enhancement for physically based materials"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1614-9531","authenticated-orcid":false,"given":"Saeed","family":"Hadadan","sequence":"first","affiliation":[{"name":"University of Maryland College Park, College Park, MD, USA and NVIDIA Research, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8799-7119","authenticated-orcid":false,"given":"Benedikt","family":"Bitterli","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6434-465X","authenticated-orcid":false,"given":"Tizian","family":"Zeltner","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-9584","authenticated-orcid":false,"given":"Jan","family":"Nov\u00e1k","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2978-2130","authenticated-orcid":false,"given":"Fabrice","family":"Rousselle","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0451-7442","authenticated-orcid":false,"given":"Jacob","family":"Munkberg","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3423-190X","authenticated-orcid":false,"given":"Jon","family":"Hasselgren","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0806-2307","authenticated-orcid":false,"given":"Bartlomiej","family":"Wronski","sequence":"additional","affiliation":[{"name":"NVIDIA Research, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8630-5515","authenticated-orcid":false,"given":"Matthias","family":"Zwicker","sequence":"additional","affiliation":[{"name":"University of Maryland College Park, College Park, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_3_2_1","unstructured":"Jingzhi Bao Xueting Li and Ming-Hsuan Yang. 2024. Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models. arXiv preprint arxiv:https:\/\/arXiv.org\/abs\/2410.10821 (2024)."},{"key":"e_1_3_3_3_3_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts Varun Jampani and Robin Rombach. 2023. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets. arXiv:https:\/\/arXiv.org\/abs\/2311.15127 (2023)."},{"key":"e_1_3_3_3_4_1","unstructured":"Brent Burley. 2012. Physically-Based Shading at Disney. SIGGRAPH 2012 Course: Physically-Based Shading."},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"e_1_3_3_3_6_1","unstructured":"Llukman Cerkezi Aram Davtyan Sepehr Sameni and Paolo Favaro. 2023. Multi-View Unsupervised Image Generation with Cross Attention Guidance. arxiv:https:\/\/arXiv.org\/abs\/2312.04337https:\/\/arxiv.org\/abs\/2312.04337"},{"key":"e_1_3_3_3_7_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chang Pascal","year":"2024","unstructured":"Pascal Chang, Jingwei Tang, Markus Gross, and Vinicius\u00a0C. Azevedo. 2024. How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=pzElnMrgSD"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_3_10_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dao Tri","year":"2024","unstructured":"Tri Dao. 2024. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"crossref","unstructured":"Giannis Daras Weili Nie Karsten Kreis Alex Dimakis Morteza Mardani Nikola\u00a0Borislavov Kovachki and Arash Vahdat. 2024. Warped diffusion: Solving video inverse problems with image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.16152 (2024).","DOI":"10.52202\/079017-3207"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"crossref","unstructured":"Matt Deitke Dustin Schwenk Jordi Salvador Luca Weihs Oscar Michel Eli VanderBilt Ludwig Schmidt Kiana Ehsani Aniruddha Kembhavi and Ali Farhadi. 2022. Objaverse: A Universe of Annotated 3D Objects. arxiv:https:\/\/arXiv.org\/abs\/2212.08051\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2212.08051","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"crossref","unstructured":"Kangle Deng Timothy Omernick Alexander Weiss Deva Ramanan Jun-Yan Zhu Tinghui Zhou and Maneesh Agrawala. 2024. FlashTex: Fast Relightable Mesh Texturing with LightControlNet. arxiv:https:\/\/arXiv.org\/abs\/2402.13251\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2402.13251","DOI":"10.1007\/978-3-031-73383-3_6"},{"key":"e_1_3_3_3_15_1","unstructured":"Juechu Dong Boyuan Feng Driss Guessous Yanbo Liang and Horace He. 2024. Flex Attention: A Programming Model for Generating Optimized Attention Kernels. arxiv:https:\/\/arXiv.org\/abs\/2412.05496\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2412.05496"},{"key":"e_1_3_3_3_16_1","unstructured":"Patrick Esser Sumith Kulal Andreas Blattmann Rahim Entezari Jonas M\u00fcller Harry Saini Yam Levi Dominik Lorenz Axel Sauer Frederic Boesel Dustin Podell Tim Dockhorn Zion English Kyle Lacey Alex Goodwin Yannik Marek and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. arxiv:https:\/\/arXiv.org\/abs\/2403.03206\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2403.03206"},{"key":"e_1_3_3_3_17_1","unstructured":"Hugging Face. 2025. Stable UnCLIP Pipeline Documentation. https:\/\/huggingface.co\/docs\/diffusers\/en\/api\/pipelines\/stable_unclip. Accessed: 2025-01-15."},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"crossref","unstructured":"Alban Gauthier Bernhard Kerbl J\u00e9r\u00e9my Levallois Robin Faury Jean-Marc Thiery and Tamy Boubekeur. 2024. MatUp: Repurposing Image Upsamplers for SVBRDFs. Computer Graphics Forum 43 4 (2024).","DOI":"10.1111\/cgf.15151"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657444"},{"key":"e_1_3_3_3_20_1","first-page":"6840","volume-title":"Advances in Neural Information Processing Systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems , H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.), Vol.\u00a033. Curran Associates, Inc., 6840\u20136851. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_3_3_21_1","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arxiv:https:\/\/arXiv.org\/abs\/2207.12598\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2207.12598"},{"key":"e_1_3_3_3_22_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hong Wenyi","year":"2023","unstructured":"Wenyi Hong, Ming Ding, Wendi Zheng, Xinghan Liu, and Jie Tang. 2023. CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"crossref","unstructured":"Wenzel Jakob and Steve Marschner. 2012. Manifold Exploration: A Markov Chain Monte Carlo Technique for Rendering Scenes with Difficult Specular Transport. ACM Transactions on Graphics (Proceedings of SIGGRAPH) 31 4 (July 2012) 58:1\u201358:13. https:\/\/doi.org\/10.1145\/2185520.2185554","DOI":"10.1145\/2185520.2335409"},{"key":"e_1_3_3_3_24_1","volume-title":"Mitsuba 3 renderer","author":"Jakob Wenzel","year":"2022","unstructured":"Wenzel Jakob, S\u00e9bastien Speierer, Nicolas Roussel, Merlin Nimier-David, Delio Vicini, Tizian Zeltner, Baptiste Nicolet, Miguel Crespo, Vincent Leroy, and Ziyi Zhang. 2022. Mitsuba 3 renderer. https:\/\/mitsuba-renderer.org."},{"key":"e_1_3_3_3_25_1","unstructured":"Yash Kant Ziyi Wu Michael Vasilkovsky Guocheng Qian Jian Ren Riza\u00a0Alp Guler Bernard Ghanem Sergey Tulyakov Igor Gilitschenski and Aliaksandr Siarohin. 2024. SPAD : Spatially Aware Multiview Diffusers. arxiv:https:\/\/arXiv.org\/abs\/2402.05235\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2402.05235"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3016"},{"key":"e_1_3_3_3_27_1","unstructured":"Benjamin Lefaudeux Francisco Massa Diana Liskovich Wenhan Xiong Vittorio Caggiano Sean Naren Min Xu Jieru Hu Marta Tintore Susan Zhang Patrick Labatut Daniel Haziza Luca Wehrstedt Jeremy Reizenstein and Grigory Sizov. 2022. xFormers: A modular and hackable Transformer modelling library. https:\/\/github.com\/facebookresearch\/xformers."},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687621"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"crossref","unstructured":"Ze Liu Han Hu Yutong Lin Zhuliang Yao Zhenda Xie Yixuan Wei Jia Ning Yue Cao Zheng Zhang Li Dong Furu Wei and Baining Guo. 2021. Swin Transformer V2: Scaling Up Capacity and Resolution. arxiv:https:\/\/arXiv.org\/abs\/2111.09883\u00a0[cs.CV]","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"e_1_3_3_3_31_1","unstructured":"Liylasviel. 2025a. ControlNet NormalBae Model (v1.1p SD15). https:\/\/huggingface.co\/lllyasviel\/control_v11p_sd15_normalbae. Accessed: 2025-01-15."},{"key":"e_1_3_3_3_32_1","unstructured":"Liylasviel. 2025b. ControlNet Tile Model (v1.1f1e SD15). https:\/\/huggingface.co\/lllyasviel\/control_v11f1e_sd15_tile. Accessed: 2025-01-15."},{"key":"e_1_3_3_3_33_1","volume-title":"International Conference on Learning Representations","author":"Meng Chenlin","year":"2022","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=aBsCjcPu_tE"},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"crossref","unstructured":"Karran Pandey Paul Guerrero Matheus Gadelha Yannick Hold-Geoffroy Karan Singh and Niloy Mitra. 2023. Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D. arxiv:https:\/\/arXiv.org\/abs\/2312.02190\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2312.02190","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"e_1_3_3_3_37_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga Alban Desmaison Andreas K\u00f6pf Edward Yang Zach DeVito Martin Raison Alykhan Tejani Sasank Chilamkurthy Benoit Steiner Lu Fang Junjie Bai and Soumith Chintala. 2019. PyTorch: An Imperative Style High-Performance Deep Learning Library. arxiv:https:\/\/arXiv.org\/abs\/1912.01703\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1912.01703"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687611"},{"key":"e_1_3_3_3_39_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_3_40_1","unstructured":"Markus\u00a0N. Rabe and Charles Staats. 2021. Self-attention Does Not Need O(n2) Memory. arxiv:https:\/\/arXiv.org\/abs\/2112.05682\u00a0[cs.LG]"},{"key":"e_1_3_3_3_41_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. arxiv:https:\/\/arXiv.org\/abs\/2204.06125\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2204.06125"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"crossref","unstructured":"Erik Reinhard Michael Stark Peter Shirley and James Ferwerda. 2002. Photographic tone reproduction for digital images. ACM Trans. Graph. 21 3 (July 2002) 267\u2013276. https:\/\/doi.org\/10.1145\/566654.566575","DOI":"10.1145\/566654.566575"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591503"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_3_45_1","unstructured":"Yichun Shi Peng Wang Jianglong Ye Long Mai Kejie Li and Xiao Yang. 2023. MVDream: Multi-view Diffusion for 3D Generation. arXiv:https:\/\/arXiv.org\/abs\/2308.16512 (2023)."},{"key":"e_1_3_3_3_46_1","unstructured":"Stability AI. 2025. Stable Diffusion 3.5 Large. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-3.5-large. Accessed: 2025-01-15."},{"key":"e_1_3_3_3_47_1","unstructured":"Shitao Tang Fuyang Zhang Jiacheng Chen Peng Wang and Yasutaka Furukawa. 2023. MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2307.01097\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2307.01097"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_3_3_49_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141\u00a0ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems , I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02087"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"crossref","unstructured":"Giuseppe Vecchio Rosalie Martin Arthur Roullier Adrien Kaiser Romain Rouffet Valentin Deschaintre and Tamy Boubekeur. 2024. ControlMat: A Controlled Generative Approach to Material Capture. ACM Trans. Graph. 43 5 Article 164 (Sept. 2024) 17\u00a0pages. https:\/\/doi.org\/10.1145\/3688830","DOI":"10.1145\/3688830"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"crossref","unstructured":"Vikram Voleti Chun-Han Yao Mark Boss Adam Letts David Pankratz Dmitry Tochilkin Christian Laforte Robin Rombach and Varun Jampani. 2024. SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion. arXiv:https:\/\/arXiv.org\/abs\/2403.12008 (2024).","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"e_1_3_3_3_53_1","unstructured":"Zhengyi Wang Cheng Lu Yikai Wang Fan Bao Chongxuan Li Hang Su and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. arXiv:https:\/\/arXiv.org\/abs\/2305.16213 (2023)."},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"crossref","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz Joe Davison Sam Shleifer Patrick von Platen Clara Ma Yacine Jernite Julien Plu Canwen Xu Teven\u00a0Le Scao Sylvain Gugger Mariama Drame Quentin Lhoest and Alexander\u00a0M. Rush. 2020. HuggingFace\u2019s Transformers: State-of-the-art Natural Language Processing. arxiv:https:\/\/arXiv.org\/abs\/1910.03771\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1910.03771","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_3_3_55_1","unstructured":"Rundi Wu Ruiqi Gao Ben Poole Alex Trevithick Changxi Zheng Jonathan\u00a0T. Barron and Aleksander Holynski. 2024. CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models. arXiv:https:\/\/arXiv.org\/abs\/2411.18613 (2024)."},{"key":"e_1_3_3_3_56_1","unstructured":"Xudong Xu Zhaoyang Lyu Xingang Pan and Bo Dai. 2023. MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.09278 (2023)."},{"key":"e_1_3_3_3_57_1","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng Da Yin Xiaotao Gu Yuxuan Zhang Weihan Wang Yean Cheng Ting Liu Bin Xu Yuxiao Dong and Jie Tang. 2024. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer."},{"key":"e_1_3_3_3_58_1","unstructured":"Taoran Yi Jiemin Fang Guanjun Wu Lingxi Xie Xiaopeng Zhang Wenyu Liu Qi Tian and Xinggang Wang. 2023. GaussianDreamer: Fast Generation from Text to 3D Gaussian Splatting with Point Cloud Priors. arxiv:https:\/\/arXiv.org\/abs\/2310.08529 (2023)."},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00416"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657445"},{"key":"e_1_3_3_3_61_1","unstructured":"Hongkun Zhang Zherong Pan Congyi Zhang Lifeng Zhu and Xifeng Gao. 2024b. TexPainter: Generative Mesh Texturing with Multi-view Consistency. arxiv:https:\/\/arXiv.org\/abs\/2406.18539\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2406.18539"},{"key":"e_1_3_3_3_62_1","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2302.05543\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2302.05543"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657504"},{"key":"e_1_3_3_3_64_1","unstructured":"Yuqing Zhang Yuan Liu Zhiyu Xie Lei Yang Zhongyuan Liu Mengzhou Yang Runze Zhang Qilong Kou Cheng Lin Wenping Wang and Xiaogang Jin. 2024a. DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2405.17176\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2405.17176"},{"key":"e_1_3_3_3_65_1","unstructured":"Junzhe Zhu and Peiye Zhuang. 2023. HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance. arXiv:https:\/\/arXiv.org\/abs\/2305.18766 (2023)."}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:02:47Z","timestamp":1774018967000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730751"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":64,"alternative-id":["10.1145\/3721238.3730751","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730751","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}