Zobrazeno 1 - 10
of 518
pro vyhledávání: '"Sunkavalli A"'
Autor:
Wu, Liwen, Bi, Sai, Xu, Zexiang, Luan, Fujun, Zhang, Kai, Georgiev, Iliyan, Sunkavalli, Kalyan, Ramamoorthi, Ravi
Novel-view synthesis of specular objects like shiny metals or glossy paints remains a significant challenge. Not only the glossy appearance but also global illumination effects, including reflections of other objects in the environment, are critical
Externí odkaz:
http://arxiv.org/abs/2405.14847
Autor:
Zhang, Kai, Bi, Sai, Tan, Hao, Xiangli, Yuanbo, Zhao, Nanxuan, Sunkavalli, Kalyan, Xu, Zexiang
We propose GS-LRM, a scalable large reconstruction model that can predict high-quality 3D Gaussian primitives from 2-4 posed sparse images in 0.23 seconds on single A100 GPU. Our model features a very simple transformer-based architecture; we patchif
Externí odkaz:
http://arxiv.org/abs/2404.19702
Autor:
Wei, Xinyue, Zhang, Kai, Bi, Sai, Tan, Hao, Luan, Fujun, Deschaintre, Valentin, Sunkavalli, Kalyan, Su, Hao, Xu, Zexiang
We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconstruction models (LRMs) that focus on NeRF-based reconstruction, MeshLRM
Externí odkaz:
http://arxiv.org/abs/2404.12385
We introduce LightIt, a method for explicit illumination control for image generation. Recent generative methods lack lighting control, which is crucial to numerous artistic aspects of image generation such as setting the overall mood or cinematic ap
Externí odkaz:
http://arxiv.org/abs/2403.10615
Autor:
Wang, Peng, Tan, Hao, Bi, Sai, Xu, Yinghao, Luan, Fujun, Sunkavalli, Kalyan, Wang, Wenping, Xu, Zexiang, Zhang, Kai
We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1.3 seconds on a single A100 GPU. PF-LR
Externí odkaz:
http://arxiv.org/abs/2311.12024
Autor:
Xu, Yinghao, Tan, Hao, Luan, Fujun, Bi, Sai, Wang, Peng, Li, Jiahao, Shi, Zifan, Sunkavalli, Kalyan, Wetzstein, Gordon, Xu, Zexiang, Zhang, Kai
We propose \textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion. Our reconstruction model incorporates a triplane NeRF representation and can denoise noisy multi-vi
Externí odkaz:
http://arxiv.org/abs/2311.09217
Autor:
Li, Jiahao, Tan, Hao, Zhang, Kai, Xu, Zexiang, Luan, Fujun, Xu, Yinghao, Hong, Yicong, Sunkavalli, Kalyan, Shakhnarovich, Greg, Bi, Sai
Text-to-3D with diffusion models has achieved remarkable progress in recent years. However, existing methods either rely on score distillation-based optimization which suffer from slow inference, low diversity and Janus problems, or are feed-forward
Externí odkaz:
http://arxiv.org/abs/2311.06214
Autor:
Hong, Yicong, Zhang, Kai, Gu, Jiuxiang, Bi, Sai, Zhou, Yang, Liu, Difan, Liu, Feng, Sunkavalli, Kalyan, Bui, Trung, Tan, Hao
We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds. In contrast to many previous methods that are trained on small-scale datasets such as ShapeNet in a categor
Externí odkaz:
http://arxiv.org/abs/2311.04400
Autor:
Athar, ShahRukh, Shu, Zhixin, Xu, Zexiang, Luan, Fujun, Bi, Sai, Sunkavalli, Kalyan, Samaras, Dimitris
Recent advances in Neural Radiance Fields (NeRFs) have made it possible to reconstruct and reanimate dynamic portrait scenes with control over head-pose, facial expressions and viewing direction. However, training such models assumes photometric cons
Externí odkaz:
http://arxiv.org/abs/2309.11009
We present a method for generating high-quality watertight manifold meshes from multi-view input images. Existing volumetric rendering methods are robust in optimization but tend to generate noisy meshes with poor topology. Differentiable rasterizati
Externí odkaz:
http://arxiv.org/abs/2305.17134