1<!DOCTYPE html> 2<html> 3 4 <head> 5 <meta charset="utf-8"> 6 <meta http-equiv="X-UA-Compatible" content="IE=edge"> 7 <meta name="viewport" content="width=device-width, initial-scale=1"> 8 <title>Chun-Han (Hank) Yao - Publications</title> 9 <meta name="description" content="Chun-Han (Hank) Yao -- Publications."> 10 <link rel="stylesheet" href="/css/main.css"> 11 <link rel="canonical" href="/publications/"> 12<link rel="shortcut icon" type ="image/x-icon" href="/images/favicon.ico"> 13 14
15<script>
vendor: 345 bytes, lines 15-21
15 16 (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ 17 (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), 18 m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) 19 })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); 20 21 ga('create', '
21UA-82472331-1
vendor: 39 bytes, lines 21-23
21', 'auto'); 22 ga('send', 'pageview'); 23
24</script>
24 25 26 27</head> 28 29 30 <body> 31 32 <div class="navbar navbar-default navbar-fixed-top" role="navigation"> 33 <div class="container-fluid"> 34 <div class="navbar-header"> 35 <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar-collapse-1" aria-expanded="false"> 36 <span class="sr-only">Toggle navigation</span> 37 <span class="icon-bar"></span> 38 <span class="icon-bar"></span> 39 <span class="icon-bar"></span> 40 </button> 41 42 <a class="navbar-brand" href="/">Chun-Han (Hank) Yao</a> 43 </div> 44 <div class="collapse navbar-collapse" id="navbar-collapse-1"> 45 <ul class="nav navbar-nav navbar-right"> 46 <li><a href="/">Home</a></li> 47 <li><a href="/publications">Publications</a></li> 48<!-- <li><a href="/codes">Codes</a></li> --> 49 <li><a href="/experience">Experience</a></li> 50 </ul> 51 </div> 52 </div> 53</div> 54 55 56 <div class="container-fluid"> 57 <div class="row"> 58 <div id="gridid" class="col-sm-12"> 59 <h3 id="publications">Publications</h3> 60 61<p>Check my <a href="https://scholar.google.com/citations?hl=en&user=866vORgAAAAJ"> Google Scholar </a> page for more up-to-date publications.</p> 62 63<div class="col-sm-11 clearfix"> 64 <div class="well"> 65 <pubtit>Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation</pubtit> 66 67 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 68 69 <!-- <p></p> --> 70 71 <p><em>Hao Zhang, Chun-Han Yao, Simon Donné, Narendra Ahuja, Varun Jampani</em></p> 72 <p>Neural Information Processing Systems (NeurIPS), 2025</p> 73 74 <p><a href="https://arxiv.org/abs/2509.10687">paper</a> 75 / 76 <a href="https://stablepartdiffusion4d.github.io/">project page</a> 77 / 78 <a href="https://www.youtube.com/watch?v=FXEFeh8tf0k">video</a> 79 / 80 <a href="https://huggingface.co/stabilityai/sp4d">model</a> 81 / 82 <a href="https://github.com/Stability-AI/generative-models/tree/sp4d">code</a></p> 83 84 </div> 85</div> 86 87<div class="col-sm-11 clearfix"> 88 <div class="well"> 89 <pubtit>SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation</pubtit> 90 91 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 92 93 <!-- <p></p> --> 94 95 <p><em>Chun-Han Yao*, Yiming Xie*, Vikram Voleti, Huaizu Jiang, Varun Jampani (* equal contribution)</em></p> 96 <p>International Conference on Computer Vision (ICCV), 2025</p> 97 98 <p><a href="https://arxiv.org/abs/2503.16396">paper</a> 99 / 100 <a href="https://sv4d20.github.io/">project page</a> 101 / 102 <a href="https://www.youtube.com/watch?v=dtqj-s50ynU">video</a> 103 / 104 <a href="https://huggingface.co/stabilityai/sv4d2.0">model</a> 105 / 106 <a href="https://github.com/Stability-AI/generative-models">code</a></p> 107 108 </div> 109</div> 110 111<div class="col-sm-11 clearfix"> 112 <div class="well"> 113 <pubtit>STABLE VIRTUAL CAMERA: Generative View Synthesis with Diffusion Models</pubtit> 114 115 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 116 117 <!-- <p></p> --> 118 119 <p><em>Jensen Jinghao Zhou*, Hang Gao*, Vikram Voleti, Aaryaman Vasishta, Chun-Han Yao, Mark Boss, Philip Torr, Christian Rupprecht, Varun Jampani (* equal contribution)</em></p> 120 <p>International Conference on Computer Vision (ICCV), 2025</p> 121 122 <p><a href="https://arxiv.org/abs/2503.14489">paper</a> 123 / 124 <a href="https://stable-virtual-camera.github.io/">project page</a> 125 / 126 <a href="https://www.youtube.com/channel/UCLLlVDcS7nNenT_zzO3OPxQ">videos</a> 127 / 128 <a href="https://huggingface.co/stabilityai/stable-virtual-camera">model</a> 129 / 130 <a href="https://github.com/Stability-AI/stable-virtual-camera">code</a> 131 / 132 <a href="https://huggingface.co/spaces/stabilityai/stable-virtual-camera">demo</a></p> 133 134 </div> 135</div> 136 137<div class="col-sm-11 clearfix"> 138 <div class="well"> 139 <pubtit>FaceCraft4D: Animated 3D Facial Avatar Generation from a Single Image</pubtit> 140 141 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 142 143 <!-- <p></p> --> 144 145 <p><em>Fei Yin, Mallikarjun B R, Chun-Han Yao, Rafal Mantiuk, Varun Jampani</em></p> 146 <p>
146International Conference on Computer Vision (ICCV), 2025</p> 147 148 <p><a href="https://arxiv.org/abs/2504.15179">paper</a> 149 / 150 <a href="https://www.cl.cam.ac.uk/~fy277/webpage/">project page</a></p> 151 152 </div> 153</div> 154 155<div class="col-sm-11 clearfix"> 156 <div class="well"> 157 <pubtit>SViM3D: Stable Video Material Diffusion for Single Image 3D Generation</pubtit> 158 159 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 160 161 <!-- <p></p> --> 162 163 <p><em>Andreas Engelhardt, Mark Boss, Vikram Voleti, Chun-Han Yao, Hendrik Lensch, Varun Jampani</em></p> 164 <p>International Conference on Computer Vision (ICCV), 2025</p> 165 166 <p><a href="https://arxiv.org/abs/2510.08271">paper</a> 167 / 168 <a href="https://svim3d.aengelhardt.com/">project page</a> 169 / 170 <a href="https://www.youtube.com/watch?v=r9XeDUGHZJ0">video</a></p> 171 172 </div> 173</div> 174 175<div class="col-sm-11 clearfix"> 176 <div class="well"> 177 <pubtit>SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency</pubtit> 178 179 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 180 181 <!-- <p></p> --> 182 183 <p><em>Yiming Xie*, Chun-Han Yao*, Vikram Voleti, Huaizu Jiang, Varun Jampani (* equal contribution)</em></p> 184 <p>International Conference on Learning Representations (ICLR), 2025</p> 185 186 <p><a href="https://arxiv.org/abs/2407.17470">paper</a> 187 / 188 <a href="https://sv4d.github.io/">project page</a> 189 / 190 <a href="https://www.youtube.com/watch?v=RBP8vdAWTgk">video</a> 191 / 192 <a href="https://huggingface.co/stabilityai/sv4d">model</a> 193 / 194 <a href="https://github.com/Stability-AI/generative-models">code</a></p> 195 196 </div> 197</div> 198 199<div class="col-sm-11 clearfix"> 200 <div class="well"> 201 <pubtit>SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion</pubtit> 202 203 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 204 205 <!-- <p></p> --> 206 207 <p><em>Vikram Voleti*, Chun-Han Yao*, Mark Boss*, Adam Letts, David Pankratz, Dmitrii Tochilkin, Christian Laforte, Robin Rombach, Varun Jampani* (* core contribution)</em></p> 208 <p>European Conference on Computer Vision (ECCV), 2024</p> 209 210 <p><a href="https://arxiv.org/abs/2306.04619">paper</a> 211 / 212 <a href="https://sv3d.github.io/">project page</a> 213 / 214 <a href="https://www.youtube.com/watch?v=Zqw4-1LcfWg">video</a> 215 / 216 <a href="https://huggingface.co/stabilityai/sv3d">model</a> 217 / 218 <a href="https://github.com/Stability-AI/generative-models">code</a></p> 219 220 </div> 221</div> 222 223<div class="col-sm-11 clearfix"> 224 <div class="well"> 225 <pubtit>ANIM: Accurate Neural Implicit Model for Human Reconstruction from a Single RGB-D Image</pubtit> 226 227 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 228 229 <!-- <p></p> --> 230 231 <p><em>Marco Pesavento, Yuanlu Xu, Nikolaos Sarafianos, Robert Maier, Ziyan Wang, Chun-Han Yao, Marco Volino, Edmond Boyer, Adrian Hilton, Tony Tung</em></p> 232 <p>Computer Vision and Pattern Recognition (CVPR), 2023</p> 233 234 <p><a href="https://openaccess.thecvf.com/content/CVPR2024/papers/Pesavento_ANIM_Accurate_Neural_Implicit_Model_for_Human_Reconstruction_from_a_CVPR_2024_paper.pdf">paper</a> 235 / 236 <a href="https://marcopesavento.github.io/ANIM/">project page</a></p> 237 238 </div> 239</div> 240 241<div class="col-sm-11 clearfix"> 242 <div class="well"> 243 <pubtit>ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections</pubtit> 244 245 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 246 247 <!-- <p></p> --> 248 249 <p><em>Chun-Han Yao, Amit Raj, Wei-Chih Hung, Yuanzhen Li, Michael Rubinstein, Ming-Hsuan Yang, Varun Jampani</em></p> 250 <p>Neural Information Processing Systems (NeurIPS), 2023</p> 251 252 <p><a href="https://arxiv.org/abs/2306.04619">paper</a> 253 / 254 <a href="https://chhankyao.github.io/artic3d/">project page</a> 255 / 256 <a href="https://www.youtube.com/watch?v=r1uKgqWlfyY">video</a> 257 / 258 <a href="https://github.com/chhankyao/artic3d_recon">
258code</a></p> 259 260 </div> 261</div> 262 263<div class="col-sm-11 clearfix"> 264 <div class="well"> 265 <pubtit>Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble</pubtit> 266 267 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 268 269 <!-- <p></p> --> 270 271 <p><em>Chun-Han Yao, Wei-Chih Hung, Yuanzhen Li, Michael Rubinstein, Ming-Hsuan Yang, Varun Jampani</em></p> 272 <p>Computer Vision and Pattern Recognition (CVPR), 2023</p> 273 274 <p><a href="https://arxiv.org/abs/2212.11042">paper</a> 275 / 276 <a href="https://chhankyao.github.io/hi-lassie/">project page</a> 277 / 278 <a href="https://www.youtube.com/watch?v=s9FWABEm0WU">video</a> 279 / 280 <a href="https://github.com/google/hi-lassie">code</a></p> 281 282 </div> 283</div> 284 285<div class="col-sm-11 clearfix"> 286 <div class="well"> 287 <pubtit>LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery</pubtit> 288 289 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 290 291 <!-- <p></p> --> 292 293 <p><em>Chun-Han Yao, Wei-Chih Hung, Yuanzhen Li, Michael Rubinstein, Ming-Hsuan Yang, Varun Jampani</em></p> 294 <p>Neural Information Processing Systems (NeurIPS), 2022</p> 295 296 <p><a href="https://arxiv.org/abs/2207.03434">paper</a> 297 / 298 <a href="https://chhankyao.github.io/lassie/">project page</a> 299 / 300 <a href="https://www.youtube.com/watch?v=MhQaHzC4Sn0">video</a> 301 / 302 <a href="https://github.com/google/lassie">code</a></p> 303 304 </div> 305</div> 306 307<div class="col-sm-11 clearfix"> 308 <div class="well"> 309 <pubtit>Learning Visibility for Robust Dense Human Body Estimation</pubtit> 310 311 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 312 313 <!-- <p></p> --> 314 315 <p><em>Chun-Han Yao, Jimei Yang, Duygu Ceylan, Yi Zhou, Yang Zhou Ming-Hsuan Yang</em></p> 316 <p>European Conference on Computer Vision (ECCV), 2022</p> 317 318 <p><a href="https://arxiv.org/abs/2208.10652">paper</a> 319 / 320 <a href="https://github.com/chhankyao/visdb">project page</a> 321 / 322 <a href="https://github.com/chhankyao/visdb">code</a></p> 323 324 </div> 325</div> 326 327<div class="col-sm-11 clearfix"> 328 <div class="well"> 329 <pubtit>Federated Multi-Target Domain Adaptation</pubtit> 330 331 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 332 333 <!-- <p></p> --> 334 335 <p><em>Chun-Han Yao, Boqing Gong, Yin Cui, Hang Qi, Yukun Zhu, Ming-Hsuan Yang</em></p> 336 <p>Winter Conference on Applications of Computer Vision (WACV), 2022</p> 337 338 <p><a href="https://arxiv.org/abs/2108.07792">paper</a></p> 339 340 </div> 341</div> 342 343<div class="col-sm-11 clearfix"> 344 <div class="well"> 345 <pubtit>Discovering 3D Parts from Image Collections</pubtit> 346 347 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 348 349 <!-- <p></p> --> 350 351 <p><em>Chun-Han Yao, Wei-Chih Hung, Varun Jampani, Ming-Hsuan Yang</em></p> 352 <p>International Conference on Computer Vision (ICCV), 2021</p> 353 354 <p><a href="https://arxiv.org/pdf/2107.13629.pdf">paper</a> 355 / 356 <a href="https://chhankyao.github.io/lpd/">project page</a> 357 / 358 <a href="https://www.youtube.com/watch?v=erNQANNwK6k">video</a> 359 / 360 <a href="https://github.com/chhankyao/lpd">code</a></p> 361 362 </div> 363</div> 364 365<div class="col-sm-11 clearfix"> 366 <div class="well"> 367 <pubtit>Video Object Detection via Object-level Temporal Aggregation</pubtit> 368 369 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 370 371 <!-- <p></p> --> 372 373 <p><em>Chun-Han Yao, Chen Fang, Xiaohui Shen, Yangyue Wan, Ming-Hsuan Yang</em></p> 374 <p>European Conference on Computer Vision (ECCV), 2020</p> 375 376 <p><a href="https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123590154.pdf">paper</a> 377 / 378 <a href="https://github.com/chhankyao/video_object_detection">code</a></p> 379 380 </div> 381</div> 382 383<div class="col-sm-11 clearfix"> 384 <div class="well"> 385 <pubtit>Progressive Domain Adaption for Object Detection</pubtit> 386 387 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 388 389 <!-- <p></p> --> 390 391 <p><em>Han-Kai Hsu, Chun-Han Yao, Yi-Hsuan Tsai, Wei-Chih Hung, Hung-Yu Tseng, Maneesh Singh, Ming-Hsuan Yang</em></p> 392 <p>Winter Conference on Applications of Computer Vision (WACV), 2020</p> 393 394 <p><a href="https://arxiv.org/abs/1910.11319">paper</a> 395 / 396 <a href="https://github.com/kevinhkhsu/DA_detection">
396code</a></p> 397 398 </div> 399</div> 400 401<div class="col-sm-11 clearfix"> 402 <div class="well"> 403 <pubtit>Occlusion-aware Video Temporal Consistency</pubtit> 404 405 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 406 407 <!-- <p></p> --> 408 409 <p><em>Chun-Han Yao, Chia-Yang Chang, Shao-Yi Chien</em></p> 410 <p>ACM Multimedia (MM), 2017</p> 411 412 <p><a href="https://dl.acm.org/doi/pdf/10.1145/3123266.3123363">paper</a> 413 / 414 <a href="https://github.com/chhankyao/video_temporal_consistency">code</a></p> 415 416 </div> 417</div> 418 419<div class="col-sm-11 clearfix"> 420 <div class="well"> 421 <pubtit>Example-based Video Color Transfer</pubtit> 422 423 <!-- <img src="/images/pubpic/" class="img-responsive" width="200px" style="float: left" /> --> 424 425 <!-- <p></p> --> 426 427 <p><em>Chun-Han Yao, Chia-Yang Chang, Shao-Yi Chien</em></p> 428 <p>IEEE International Conference on Multimedia and Expo (ICME), 2016</p> 429 430 <p><a href="https://ieeexplore.ieee.org/abstract/document/7552926">paper</a> 431 / 432 <a href="https://github.com/chhankyao/video_color_transfer">code</a></p> 433 434 </div> 435</div> 436 437<p> Â </p> 438 439</div> 440 441 </div> 442 </div> 443 444 <div id="footer" class="panel"> 445 <div class="panel-footer"> 446 <div class="container-fluid"> 447 <div class="row"> 448 <div class="col-sm-5"> 449 450 <p>Site made with <a href="https://jekyllrb.com">Jekyll</a>.</p> 451 <p> </p><p> 452 453 454 </div> 455 <div class="col-sm-5"> 456 </div> 457 <div class="col-sm-5"> 458 </div> 459 <div class="col-sm-5"> 460 </div> 461 </div> 462 </div> 463 </div> 464</div> 465
466<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.3/jquery.min.js"></script>
vendor: 1 bytes, line 466
466
467<script src="/js/bootstrap.min.js"></script>
467 468 469 470 </body> 471 472</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.