Results 241 to 248 of about 2,709,443 (248)

VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior

International Conference on 3D Vision, 2023
Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, facial motion, head pose generation, and video quality.
Xusen Sun, Longhao Zhang, Hao Zhu, Peng Zhang, Bang Zhang, Xinya Ji, Kangneng Zhou, Daiheng Gao, Liefeng Bo, Xun Cao   +9 more
semanticscholar   +1 more source

Gen3DSR: Generalizable 3D Scene Reconstruction Via Divide and Conquer From a Single View

International Conference on 3D Vision
Single-view 3D reconstruction is currently approached from two dominant perspectives: reconstruction of scenes with limited diversity using 3D data supervision or reconstruction of diverse singular objects using large image priors.
Andreea Dogaru, M. Ozer, Bernhard Egger
semanticscholar   +1 more source

Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting

International Conference on 3D Vision
While text-to-3D and image-to-3D generation tasks have received considerable attention, one important but under-explored field between them is controllable text-to-3D generation, which we mainly focus on in this work.
Zhiqi Li, Yiming Chen, Lingzhe Zhao, Peidong Liu   +3 more
semanticscholar   +1 more source

An Object is Worth 64×64 Pixels: Generating 3D Object via Image Diffusion

International Conference on 3D Vision
We introduce a new approach for generating realistic 3D models with UV maps through a representation termed “Object Images.” This approach encapsulates surface geometry, appearance, and patch structures within a 64×64 pixel image, effectively converting ...
Xingguang Yan, Han-Hung Lee, Ziyu Wan, Angel X. Chang   +3 more
semanticscholar   +1 more source

Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model

International Conference on 3D Vision
Recent advancements in multimodal large language models (LLMs) have demonstrated significant potential across various domains, particularly in concept reasoning.
Kuan-Chih Huang, Xiangtai Li, Lu Qi, Shuicheng Yan, Ming-Hsuan Yang   +4 more
semanticscholar   +1 more source

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting

International Conference on 3D Vision
3D scene generation has quickly become a challenging new research direction, fueled by consistent improvements of 2D generative diffusion models. Current methods generate scenes by iteratively stitching newly generated images with existing geometry ...
Paul Engstler, Andrea Vedaldi, Iro Laina, Christian Rupprecht   +3 more
semanticscholar   +1 more source

Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces

International Conference on 3D Vision
Touch and vision go hand in hand, mutually enhancing our ability to understand the world. From a research perspective, the problem of mixing touch and vision together is underexplored and presents interesting challenges.
Mauro Comi, Alessio Tonioni, Max Yang, Jonathan Tremblay, Valts Blukis, Yijiong Lin, N. Lepora, Laurence Aitchison   +7 more
semanticscholar   +1 more source

Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions

International Conference on 3D Vision
We introduce Joker, a new method for the conditional synthesis of 3D human heads with extreme expressions. Given a single reference image of a person, we synthesize a volumetric human head with the reference's identity and a new expression.
Malte Prinzler, Egor Zakharov, V. Sklyarova, Berna Kabadayi, Justus Thies   +4 more
semanticscholar   +1 more source