Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Kokkinos, Filippos"'
Autor:
Bensadoun, Raphael, Monnier, Tom, Kleiman, Yanir, Kokkinos, Filippos, Siddiqui, Yawar, Kariya, Mahendra, Harosh, Omri, Shapovalov, Roman, Graham, Benjamin, Garreau, Emilien, Karnewar, Animesh, Cao, Ang, Azuri, Idan, Makarov, Iurii, Le, Eric-Tuan, Toisoul, Antoine, Novotny, David, Gafni, Oran, Neverova, Natalia, Vedaldi, Andrea
We introduce Meta 3D Gen (3DGen), a new state-of-the-art, fast pipeline for text-to-3D asset generation. 3DGen offers 3D asset creation with high prompt fidelity and high-quality 3D shapes and textures in under a minute. It supports physically-based
Externí odkaz:
http://arxiv.org/abs/2407.02599
Autor:
Siddiqui, Yawar, Monnier, Tom, Kokkinos, Filippos, Kariya, Mahendra, Kleiman, Yanir, Garreau, Emilien, Gafni, Oran, Neverova, Natalia, Vedaldi, Andrea, Shapovalov, Roman, Novotny, David
We present Meta 3D AssetGen (AssetGen), a significant advancement in text-to-3D generation which produces faithful, high-quality meshes with texture and material control. Compared to works that bake shading in the 3D object's appearance, AssetGen out
Externí odkaz:
http://arxiv.org/abs/2407.02445
Procedural Content Generation (PCG) algorithms enable the automatic generation of complex and diverse artifacts. However, they don't provide high-level control over the generated content and typically require domain expertise. In contrast, text-to-3D
Externí odkaz:
http://arxiv.org/abs/2404.15538
This paper presents a novel method for building scalable 3D generative models utilizing pre-trained video diffusion models. The primary obstacle in developing foundation 3D generative models is the limited availability of 3D data. Unlike images, text
Externí odkaz:
http://arxiv.org/abs/2403.12034
Autor:
Melas-Kyriazi, Luke, Laina, Iro, Rupprecht, Christian, Neverova, Natalia, Vedaldi, Andrea, Gafni, Oran, Kokkinos, Filippos
Most text-to-3D generators build upon off-the-shelf text-to-image models trained on billions of images. They use variants of Score Distillation Sampling (SDS), which is slow, somewhat unstable, and prone to artifacts. A mitigation is to fine-tune the
Externí odkaz:
http://arxiv.org/abs/2402.08682
Autor:
Shapovalov, Roman, Kleiman, Yanir, Rocco, Ignacio, Novotny, David, Vedaldi, Andrea, Chen, Changan, Kokkinos, Filippos, Graham, Ben, Neverova, Natalia
We introduce Replay, a collection of multi-view, multi-modal videos of humans interacting socially. Each scene is filmed in high production quality, from different viewpoints with several static cameras, as well as wearable action cameras, and record
Externí odkaz:
http://arxiv.org/abs/2307.12067
Autor:
Rocco, Ignacio, Makarov, Iurii, Kokkinos, Filippos, Novotny, David, Graham, Benjamin, Neverova, Natalia, Vedaldi, Andrea
We present a method for fast 3D reconstruction and real-time rendering of dynamic humans from monocular videos with accompanying parametric body fits. Our method can reconstruct a dynamic human in less than 3h using a single GPU, compared to recent s
Externí odkaz:
http://arxiv.org/abs/2303.11898
Autor:
Singer, Uriel, Sheynin, Shelly, Polyak, Adam, Ashual, Oron, Makarov, Iurii, Kokkinos, Filippos, Goyal, Naman, Vedaldi, Andrea, Parikh, Devi, Johnson, Justin, Taigman, Yaniv
We present MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. Our approach uses a 4D dynamic Neural Radiance Field (NeRF), which is optimized for scene appearance, density, and motion consistency
Externí odkaz:
http://arxiv.org/abs/2301.11280
Autor:
Babiloni, Francesca, Marras, Ioannis, Kokkinos, Filippos, Deng, Jiankang, Chrysos, Grigorios, Zafeiriou, Stefanos
Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions. Such pairwise functions underpin the effectiveness of
Externí odkaz:
http://arxiv.org/abs/2107.02859
Autor:
Kokkinos, Filippos, Kokkinos, Iasonas
We present To The Point (TTP), a method for reconstructing 3D objects from a single image using 2D to 3D correspondences learned from weak supervision. We recover a 3D shape from a 2D image by first regressing the 2D positions corresponding to the 3D
Externí odkaz:
http://arxiv.org/abs/2106.05662