{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:50Z","timestamp":1778048510219,"version":"3.51.4"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010097","name":"China Association for Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010097","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00130","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1273-1283","source":"Crossref","is-referenced-by-count":0,"title":["PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models"],"prefix":"10.1109","author":[{"given":"Zilu","family":"Guo","sequence":"first","affiliation":[{"name":"FNii-Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Lin","sequence":"additional","affiliation":[{"name":"FNii-Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Yuan","sequence":"additional","affiliation":[{"name":"FNii-Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoda","family":"Zheng","sequence":"additional","affiliation":[{"name":"FNii-Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengshuo","family":"Qiu","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongzhi","family":"Jiang","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Mei","family":"Feng","sequence":"additional","affiliation":[{"name":"University College Dublin,Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"CUHK-Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Self-improving diffusion models with synthetic data","author":"Alemohammad","year":"2024"},{"key":"ref2","author":"Alemohammad","year":"2024","journal-title":"Self-improving diffusion models with synthetic data"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.78"},{"key":"ref4","article-title":"Mint-cot: Enabling interleaved visual tokens in mathematical chain-of-thought reasoning","author":"Chen","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref7","article-title":"Efficient self-improvement in multimodal large language mod-els: A model-level judge-free approach","author":"Deng","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4175"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref10","article-title":"Multimodal-gpt: A vision and language model for dialogue with humans","author":"Gong","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref12","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023"},{"key":"ref13","article-title":"Sam2point: Segment any 3d as videos in zero-shot and promptable manners","author":"Guo","year":"2024"},{"key":"ref14","article-title":"Can we generate images with cot? let\u2019s verify and reinforce image generation step by step","author":"Guo","year":"2025"},{"key":"ref15","article-title":"Imagebind-llm: Multi-modality instruction tuning","author":"Han","year":"2023"},{"key":"ref16","article-title":"3d-llm: Injecting the 3d world into large language models","author":"Hong","year":"2023","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref18","article-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","author":"Huang","year":"2023"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"ref21","article-title":"Mmsearch: Benchmarking the potential of large models as multi-modal search engines","author":"Jiang","year":"2024"},{"key":"ref22","article-title":"T2i-r1: Reinforcing image generation with collaborative semantic-level and token-level cot","author":"Jiang","year":"2025"},{"key":"ref23","article-title":"Mme-cot: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency","author":"Jiang","year":"2025"},{"key":"ref24","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.421"},{"key":"ref26","author":"Liu","year":"2023","journal-title":"Visual instruction tuning"},{"key":"ref27","article-title":"Scalable 3d captioning with pretrained models","author":"Luo","year":"2023"},{"key":"ref28","article-title":"View selection for 3d captioning via diffusion ranking","author":"Luo","year":"2024"},{"key":"ref29","article-title":"Gpt-4 technical report","year":"2024"},{"key":"ref30","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Peng","year":"2023"},{"key":"ref31","article-title":"Shapellm: Universal 3d object understanding for embodied interaction","author":"Qi","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02495"},{"key":"ref33","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref34","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.157060"},{"key":"ref37","article-title":"Delving into rl for image generation with cot: A study on dpo vs. grpo","author":"Tong","year":"2025"},{"key":"ref38","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref42","article-title":"Blink-twice: You see, but do you observe? a reasoning benchmark on visual perception","author":"Ye","year":"2025"},{"key":"ref43","article-title":"Echo-4o: Harnessing the power of gpt4o synthetic images for improved image generation","author":"Ye","year":"2025"},{"key":"ref44","article-title":"Self-play fine-tuning of diffusion models for text-to-image generation","author":"Yuan","year":"2024"},{"key":"ref45","article-title":"Reinforcement learning from human feedback: Challenges and opportunities","author":"Yuan","year":"2024"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-73242-3_10","article-title":"Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems?","volume-title":"ECCV 2024","author":"Zhang"},{"key":"ref47","article-title":"Mavis: Mathematical visual instruction tuning with an automatic data engine","author":"Zhang","year":"2024"},{"key":"ref48","article-title":"Uni3d: Exploring unified 3d representation at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhou"},{"key":"ref49","article-title":"Lima: Less is more for alignment","author":"Zhou","year":"2023"},{"key":"ref50","article-title":"Easyref: Omni-generalized group image reference for diffusion models via multimodal llm","author":"Zong","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3282"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491983.pdf?arnumber=11491983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:08:38Z","timestamp":1778047718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00130","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}