Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses

• URL: http://arxiv.org/abs/2404.14410v1
• Date: Mon, 22 Apr 2024 17:59:50 GMT
• Title: Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses
• Authors: Inhee Lee, Byungjun Kim, Hanbyul Joo,
• Abstract summary: We present a method to reconstruct the world and multiple dynamic humans in 3D from a monocular video input. As a key idea, we represent both the world and multiple humans via the recently emerging 3D Gaussian Splatting (3D-GS) representation.
• Score: 9.529416246409355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present a method to reconstruct the world and multiple dynamic humans in 3D from a monocular video input. As a key idea, we represent both the world and multiple humans via the recently emerging 3D Gaussian Splatting (3D-GS) representation, enabling to conveniently and efficiently compose and render them together. In particular, we address the scenarios with severely limited and sparse observations in 3D human reconstruction, a common challenge encountered in the real world. To tackle this challenge, we introduce a novel approach to optimize the 3D-GS representation in a canonical space by fusing the sparse cues in the common space, where we leverage a pre-trained 2D diffusion model to synthesize unseen views while keeping the consistency with the observed 2D appearances. We demonstrate our method can reconstruct high-quality animatable 3D humans in various challenging examples, in the presence of occlusion, image crops, few-shot, and extremely sparse observations. After reconstruction, our method is capable of not only rendering the scene in any novel views at arbitrary time instances, but also editing the 3D scene by removing individual humans or applying different motions for each human. Through various experiments, we demonstrate the quality and efficiency of our methods over alternative existing approaches.

Related papers

• DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans [38.8751809679184]
  We present DiffHuman, a probabilistic method for 3D human reconstruction from a single RGB image. Our experiments show that DiffHuman can produce diverse and detailed reconstructions for the parts of the person that are unseen or uncertain in the input image.
  arXiv  Detail & Related papers  (2024-03-30T22:28:29Z)
• 3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation [51.64796781728106]
  We propose a generative refinement network to synthesize new contents with higher quality by exploiting the natural image prior to 2D diffusion model and the global 3D information of the current scene. Our approach supports wide variety of scene generation and arbitrary camera trajectories with improved visual quality and 3D consistency.
  arXiv  Detail & Related papers  (2024-03-14T14:31:22Z)
• Denoising Diffusion via Image-Based Rendering [54.20828696348574]
  We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
  arXiv  Detail & Related papers  (2024-02-05T19:00:45Z)
• Generative Novel View Synthesis with 3D-Aware Diffusion Models [96.78397108732233]
  We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our method makes use of existing 2D diffusion backbones but, crucially, incorporates geometry priors in the form of a 3D feature volume. In addition to generating novel views, our method has the ability to autoregressively synthesize 3D-consistent sequences.
  arXiv  Detail & Related papers  (2023-04-05T17:15:47Z)
• SHERF: Generalizable Human NeRF from a Single Image [59.10589479808622]
  SHERF is the first generalizable Human NeRF model for recovering animatable 3D humans from a single input image. We propose a bank of 3D-aware hierarchical features, including global, point-level, and pixel-aligned features, to facilitate informative encoding.
  arXiv  Detail & Related papers  (2023-03-22T17:59:12Z)
• Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition [40.46674919612935]
  We present Vid2Avatar, a method to learn human avatars from monocular in-the-wild videos. Our method does not require any groundtruth supervision or priors extracted from large datasets of clothed human scans. It solves the tasks of scene decomposition and surface reconstruction directly in 3D by modeling both the human and the background in the scene jointly.
  arXiv  Detail & Related papers  (2023-02-22T18:59:17Z)
• Scene-Aware 3D Multi-Human Motion Capture from a Single Camera [83.06768487435818]
  We consider the problem of estimating the 3D position of multiple humans in a scene as well as their body shape and articulation from a single RGB video recorded with a static camera. We leverage recent advances in computer vision using large-scale pre-trained models for a variety of modalities, including 2D body joints, joint angles, normalized disparity maps, and human segmentation masks. In particular, we estimate the scene depth and unique person scale from normalized disparity predictions using the 2D body joints and joint angles.
  arXiv  Detail & Related papers  (2023-01-12T18:01:28Z)
• 3inGAN: Learning a 3D Generative Model from Images of a Self-similar Scene [34.2144933185175]
  3inGAN is an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene. We show results on semi-stochastic scenes of varying scale and complexity, obtained from real and synthetic sources.
  arXiv  Detail & Related papers  (2022-11-27T18:03:21Z)
• HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance [82.09463058198546]
  Marker-less monocular 3D human motion capture (MoCap) with scene interactions is a challenging research topic relevant for extended reality, robotics and virtual avatar generation. We propose HULC, a new approach for 3D human MoCap which is aware of the scene geometry.
  arXiv  Detail & Related papers  (2022-05-11T17:59:31Z)

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.