MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling

• URL: http://arxiv.org/abs/2409.16160v1
• Date: Tue, 24 Sep 2024 15:00:07 GMT
• Title: MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling
• Authors: Yifang Men, Yuan Yao, Miaomiao Cui, Liefeng Bo,
• Abstract summary: Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. Milo is a novel framework which can synthesize character videos with controllable attributes. Milo achieves advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes.
• Score: 21.1274747033854
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their applicability of modeling arbitrary characters in a short time. Recent 2D methods break this limitation via pre-trained diffusion models, but they struggle for pose generality and scene interaction. To this end, we propose MIMO, a novel framework which can not only synthesize character videos with controllable attributes (i.e., character, motion and scene) provided by simple user inputs, but also simultaneously achieve advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes in a unified framework. The core idea is to encode the 2D video to compact spatial codes, considering the inherent 3D nature of video occurrence. Concretely, we lift the 2D frame pixels into 3D using monocular depth estimators, and decompose the video clip to three spatial components (i.e., main human, underlying scene, and floating occlusion) in hierarchical layers based on the 3D depth. These components are further encoded to canonical identity code, structured motion code and full scene code, which are utilized as control signals of synthesis process. The design of spatial decomposed modeling enables flexible user control, complex motion expression, as well as 3D-aware synthesis for scene interactions. Experimental results demonstrate effectiveness and robustness of the proposed method.

Related papers

• Generating 3D-Consistent Videos from Unposed Internet Photos [68.944029293283]
  We train a scalable, 3D-aware video model without any 3D annotations such as camera parameters. Our results suggest that we can scale up scene-level 3D learning using only 2D data such as videos and multiview internet photos.
  arXiv  Detail & Related papers  (2024-11-20T18:58:31Z)
• Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketches [50.51643519253066]
  3D Content Generation is at the heart of many computer graphics applications, including video gaming, film-making, virtual and augmented reality, etc. This paper proposes a novel deep-learning based approach for automatically generating interactive and playable 3D game scenes.
  arXiv  Detail & Related papers  (2024-08-08T16:27:37Z)
• Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering [57.895846642868904]
  We present a 3D generative model named DynaVol-S for dynamic scenes that enables object-centric learning. voxelization infers per-object occupancy probabilities at individual spatial locations. Our approach integrates 2D semantic features to create 3D semantic grids, representing the scene through multiple disentangled voxel grids.
  arXiv  Detail & Related papers  (2024-07-30T15:33:58Z)
• GenZI: Zero-Shot 3D Human-Scene Interaction Generation [39.9039943099911]
  We propose GenZI, the first zero-shot approach to generating 3D human-scene interactions. Key to GenZI is our distillation of interaction priors from large vision-language models (VLMs), which have learned a rich semantic space of 2D human-scene compositions. In contrast to existing learning-based approaches, GenZI circumvents the conventional need for captured 3D interaction data.
  arXiv  Detail & Related papers  (2023-11-29T15:40:11Z)
• Blocks2World: Controlling Realistic Scenes with Editable Primitives [5.541644538483947]
  We present Blocks2World, a novel method for 3D scene rendering and editing. Our technique begins by extracting 3D parallelepipeds from various objects in a given scene using convex decomposition. The next stage involves training a conditioned model that learns to generate images from the 2D-rendered convex primitives.
  arXiv  Detail & Related papers  (2023-07-07T21:38:50Z)
• MoDA: Modeling Deformable 3D Objects from Casual Videos [84.29654142118018]
  We propose neural dual quaternion blend skinning (NeuDBS) to achieve 3D point deformation without skin-collapsing artifacts. In the endeavor to register 2D pixels across different frames, we establish a correspondence between canonical feature embeddings that encodes 3D points within the canonical space. Our approach can reconstruct 3D models for humans and animals with better qualitative and quantitative performance than state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-17T13:49:04Z)
• CC3D: Layout-Conditioned Generation of Compositional 3D Scenes [49.281006972028194]
  We introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts. Our evaluations on synthetic 3D-FRONT and real-world KITTI-360 datasets demonstrate that our model generates scenes of improved visual and geometric quality.
  arXiv  Detail & Related papers  (2023-03-21T17:59:02Z)
• Playable Environments: Video Manipulation in Space and Time [98.0621309257937]
  We present Playable Environments - a new representation for interactive video generation and manipulation in space and time. With a single image at inference time, our novel framework allows the user to move objects in 3D while generating a video by providing a sequence of desired actions. Our method builds an environment state for each frame, which can be manipulated by our proposed action module and decoded back to the image space with volumetric rendering.
  arXiv  Detail & Related papers  (2022-03-03T18:51:05Z)
• Action2video: Generating Videos of Human 3D Actions [31.665831044217363]
  We aim to tackle the interesting yet challenging problem of generating videos of diverse and natural human motions from prescribed action categories. Key issue lies in the ability to synthesize multiple distinct motion sequences that are realistic in their visual appearances. Action2motionally generates plausible 3D pose sequences of a prescribed action category, which are processed and rendered by motion2video to form 2D videos.
  arXiv  Detail & Related papers  (2021-11-12T20:20:37Z)

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.