Meta tags:
author= Xiuchao Wu;
Headings (most frequently used words):
-
Text of the page (most frequently used words):
rendering (10), paper (8), xiuchao (8), neural (7), weiwei (7), and (7), reconstruction (6), scalable (6), video (6), project (6), material (6), with (5), for (5), scene (5), this (4), based (4), indoor (4), siggraph (4), qixing (4), huang (4), zhu (4), jiamin (4), view (4), diffusion (4), lyu (4), guo (4), image (3), acm (3), transactions (3), graphics (3), tog (3), hujun (3), bao (3), large (3), james (3), tompkin (3), fields (3), local (3), from (3), model (3), estimation (3), matmart (3), generation (3), representation (2), novel (2), scenes (2), reflections (2), zihan (2), high (2), quality (2), scale (2), research (2), optimization (2), radiance (2), asia (2), density (2), gaussian (2), mixtures (2), ray (2), input (2), images (2), stableintrinsic (2), one (2), step (2), multi (2), chengfei (2), yanwen (2), jie (2), xinguo (2), liu (2), jiangjing (2), pengfei (2), end (2), technology (2), zhejiang (2), university (2), 吴秀超 (2), experience, 一等奖, the, first, prize, among, 466, teams, implicit, 粤港澳大湾区, 国际算法算例大赛, 神经隐式表示的物体三维重建, awards, proposes, ibr, pipeline, 2021, yin, yang, propose, method, support, distributed, training, interactive, 2022, requires, accurate, camera, poses, combines, tile, hybrid, parallel, distributive, improve, bundleadjusting, 2023, yujun, shen, xin, zhang, scanerf, bundle, adjusting, approach, uses, per, represented, along, each, synthesize, views, warp, fuse, volumes, then, alpha, composite, using, photograph, colors, small, set, neighboring, 2024, yifan, peng, chi, wang, unstructured, lumigraph, introduce, that, can, produce, parameters, low, variance, preprint, https, arxiv, org, pdf, 2508, 19789, detail, preserving, adopts, two, stage, enables, arbitrary, number, achieves, both, prediction, capabilities, through, single, cvpr, 2026, objects, via, publications, now, working, tao, department, alibaba, group, received, phd, state, key, lab, cad, where, was, supervised, prof, did, undergrad, interests, are, asset, synthesis, mail, wuxiuchao, zju, edu, home, page,
Text of the page (random words):
xiuchao wu 吴秀超 home page xiuchao wu 吴秀超 i m now working at tao technology department alibaba group i received my phd from zhejiang university state key lab of cad cg where i was supervised by prof weiwei xu i did my undergrad at zhejiang university of technology my research interests are 3d asset generation material estimation generation 3d reconstruction neural rendering view synthesis and image based rendering e mail wuxiuchao zju edu cn publications matmart material reconstruction of 3d objects via diffusion xiuchao wu pengfei zhu jiangjing lyu xinguo liu jie guo yanwen guo weiwei xu chengfei lyu cvpr 2026 project paper video matmart adopts a two stage reconstruction and enables reconstruction from an arbitrary number of input images matmart achieves both material prediction and generation capabilities through end to end optimization of a single diffusion model stableintrinsic detail preserving one step diffusion model for multi view material estimation xiuchao wu pengfei zhu jiangjing lyu xinguo liu jie guo yanwen guo weiwei xu chengfei lyu preprint https arxiv org pdf 2508 19789 project paper video in this paper we introduce stableintrinsic a one step diffusion model for multi view material estimation that can produce high quality material parameters with low variance local gaussian density mixtures for unstructured lumigraph rendering xiuchao wu jiamin xu chi wang yifan peng qixing huang james tompkin weiwei xu siggraph asia 2024 project paper video this approach uses a local or per view density represented as gaussian mixtures along each ray to synthesize novel views we warp and fuse local volumes then alpha composite using input photograph ray colors from a small set of neighboring images scanerf scalable bundle adjusting neural radiance fields for large scale scene rendering xiuchao wu jiamin xu xin zhang hujun bao qixing huang yujun shen james tompkin weiwei xu siggraph asia 2023 acm transactions on graphics tog project paper video high quality large scale scene rendering requires a scalable representation and accurate camera poses this research combines tile based hybrid neural fields with parallel distributive optimization to improve bundleadjusting neural radiance fields scalable neural indoor scene rendering xiuchao wu jiamin xu zihan zhu hujun bao qixing huang james tompkin weiwei xu siggraph 2022 acm transactions on graphics tog project paper video we propose a scalable neural scene reconstruction and rendering method to support distributed training and interactive rendering of large indoor scenes scalable image based indoor scene rendering with reflections jiamin xu xiuchao wu zihan zhu qixing huang yin yang hujun bao weiwei xu siggraph 2021 acm transactions on graphics tog project paper video this paper proposes a novel scalable image based rendering ibr pipeline for indoor scenes with reflections awards 粤港澳大湾区 黄埔 国际算法算例大赛 神经隐式表示的物体三维重建 3d reconstruction with neural implicit representation 一等奖 the first prize among 466 teams experience
|
