PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting

• URL: http://arxiv.org/abs/2405.19957v3
• Date: Wed, 5 Jun 2024 12:35:09 GMT
• Title: PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting
• Authors: Qiaowei Miao, Yawei Luo, Yi Yang,
• Abstract summary: We propose text-to-video frames as explicit pixel alignment targets to generate static 3D objects and inject motion into them. We develop Motion Alignment using a deformation network to drive changes in Gaussians and implement Reference Refinement for smooth 4D object surfaces. Compared to previous methods, PLA4D produces synthesized outputs with better texture details in less time and effectively mitigates the Janus-faced problem.
• Score: 26.382349137191547
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As text-conditioned diffusion models (DMs) achieve breakthroughs in image, video, and 3D generation, the research community's focus has shifted to the more challenging task of text-to-4D synthesis, which introduces a temporal dimension to generate dynamic 3D objects. In this context, we identify Score Distillation Sampling (SDS), a widely used technique for text-to-3D synthesis, as a significant hindrance to text-to-4D performance due to its Janus-faced and texture-unrealistic problems coupled with high computational costs. In this paper, we propose \textbf{P}ixel-\textbf{L}evel \textbf{A}lignments for Text-to-\textbf{4D} Gaussian Splatting (\textbf{PLA4D}), a novel method that utilizes text-to-video frames as explicit pixel alignment targets to generate static 3D objects and inject motion into them. Specifically, we introduce Focal Alignment to calibrate camera poses for rendering and GS-Mesh Contrastive Learning to distill geometry priors from rendered image contrasts at the pixel level. Additionally, we develop Motion Alignment using a deformation network to drive changes in Gaussians and implement Reference Refinement for smooth 4D object surfaces. These techniques enable 4D Gaussian Splatting to align geometry, texture, and motion with generated videos at the pixel level. Compared to previous methods, PLA4D produces synthesized outputs with better texture details in less time and effectively mitigates the Janus-faced problem. PLA4D is fully implemented using open-source models, offering an accessible, user-friendly, and promising direction for 4D digital content creation. Our project page: https://miaoqiaowei.github.io/PLA4D/.

Related papers

• Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models [54.35214051961381]
  3D meshes are widely used in computer vision and graphics for their efficiency in animation and minimal memory use in movies, games, AR, and VR. However, creating temporal consistent and realistic textures for mesh remains labor-intensive for professional artists. We present 3D Tex sequences that integrates inherent geometry from mesh sequences with video diffusion models to produce consistent textures.
  arXiv  Detail & Related papers  (2024-10-14T17:59:59Z)
• Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis [60.853577108780414]
  Existing 4D generation methods can generate high-quality 4D objects or scenes based on user-friendly conditions. We propose Trans4D, a novel text-to-4D synthesis framework that enables realistic complex scene transitions. In experiments, Trans4D consistently outperforms existing state-of-the-art methods in generating 4D scenes with accurate and high-quality transitions.
  arXiv  Detail & Related papers  (2024-10-09T17:56:03Z)
• BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis [9.376238965029819]
  This paper presents BrightDreamer, an end-to-end single-stage approach that can achieve generalizable and fast (77 ms) text-to-3D generation. We first propose a Text-guided Shape Deformation (TSD) network to predict the deformed shape and its new positions. We then design a novel Text-guided Triplane Generator to generate a triplane representation for a 3D object.
  arXiv  Detail & Related papers  (2024-03-17T17:04:45Z)
• 4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency [118.15258850780417]
  This work introduces 4DGen, a novel framework for grounded 4D content creation. We identify static 3D assets and monocular video sequences as key components in constructing the 4D content. Our pipeline facilitates conditional 4D generation, enabling users to specify geometry (3D assets) and motion (monocular videos)
  arXiv  Detail & Related papers  (2023-12-28T18:53:39Z)
• Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models [94.07744207257653]
  We focus on the underexplored text-to-4D setting and synthesize dynamic, animated 3D objects. We combine text-to-image, text-to-video, and 3D-aware multiview diffusion models to provide feedback during 4D object optimization.
  arXiv  Detail & Related papers  (2023-12-21T11:41:02Z)
• 4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling [91.99172731031206]
  Current text-to-4D methods face a three-way tradeoff between quality of scene appearance, 3D structure, and motion. We introduce hybrid score distillation sampling, an alternating optimization procedure that blends supervision signals from multiple pre-trained diffusion models.
  arXiv  Detail & Related papers  (2023-11-29T18:58:05Z)
• Text-To-4D Dynamic Scene Generation [111.89517759596345]
  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. The dynamic video output generated from the provided text can be viewed from any camera location and angle, and can be composited into any 3D environment.
  arXiv  Detail & Related papers  (2023-01-26T18:14:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.