Zobrazeno 1 - 10
of 380
pro vyhledávání: '"LI, Kejie"'
Recent advancements in text-to-3D generation, building on the success of high-performance text-to-image generative models, have made it possible to create imaginative and richly textured 3D objects from textual descriptions. However, a key challenge
Externí odkaz:
http://arxiv.org/abs/2411.11475
This paper introduces Camera-free Diffusion (CamFreeDiff) model for 360-degree image outpainting from a single camera-free image and text description. This method distinguishes itself from existing strategies, such as MVDiffusion, by eliminating the
Externí odkaz:
http://arxiv.org/abs/2407.07174
Leveraging neural implicit representation to conduct dense RGB-D SLAM has been studied in recent years. However, this approach relies on a static environment assumption and does not work robustly within a dynamic environment due to the inconsistent o
Externí odkaz:
http://arxiv.org/abs/2407.01303
Using image as prompts for 3D generation demonstrate particularly strong performances compared to using text prompts alone, for images provide a more intuitive guidance for the 3D generation process. In this work, we delve into the potential of using
Externí odkaz:
http://arxiv.org/abs/2404.17419
Leveraging multi-view diffusion models as priors for 3D optimization have alleviated the problem of 3D consistency, e.g., the Janus face problem or the content drift problem, in zero-shot text-to-3D models. However, the 3D geometric fidelity of the o
Externí odkaz:
http://arxiv.org/abs/2404.10603
Zero-shot novel view synthesis (NVS) from a single image is an essential problem in 3D object understanding. While recent approaches that leverage pre-trained generative models can synthesize high-quality novel views from in-the-wild inputs, they sti
Externí odkaz:
http://arxiv.org/abs/2310.03020
We introduce MVDream, a diffusion model that is able to generate consistent multi-view images from a given text prompt. Learning from both 2D and 3D data, a multi-view diffusion model can achieve the generalizability of 2D diffusion models and the co
Externí odkaz:
http://arxiv.org/abs/2308.16512
In recent years, neural implicit surface reconstruction has emerged as a popular paradigm for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural implicit surface-based methods leverage neural networks to represe
Externí odkaz:
http://arxiv.org/abs/2308.07868
Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image. The existi
Externí odkaz:
http://arxiv.org/abs/2307.14570
Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of implicit rep
Externí odkaz:
http://arxiv.org/abs/2305.13312