ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Events

• URL: http://arxiv.org/abs/2409.14103v1
• Date: Sat, 21 Sep 2024 10:58:01 GMT
• Title: ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Events
• Authors: Kanghao Chen, Zeyu Wang, Lin Wang,
• Abstract summary: We propose ExFMan, the first neural rendering framework that renders high-quality humans in rapid motion with a hybrid frame-based RGB and bio-inspired event camera. We first formulate a velocity field of the 3D body in the canonical space and render it to image space to identify the body parts with motion blur. We then propose two novel losses, i.e., velocity-aware photometric loss and velocity-relative event loss, to optimize the neural human for both modalities.
• Score: 7.820081911598502
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent years have witnessed tremendous progress in the 3D reconstruction of dynamic humans from a monocular video with the advent of neural rendering techniques. This task has a wide range of applications, including the creation of virtual characters for virtual reality (VR) environments. However, it is still challenging to reconstruct clear humans when the monocular video is affected by motion blur, particularly caused by rapid human motion (e.g., running, dancing), as often occurs in the wild. This leads to distinct inconsistency of shape and appearance for the rendered 3D humans, especially in the blurry regions with rapid motion, e.g., hands and legs. In this paper, we propose ExFMan, the first neural rendering framework that unveils the possibility of rendering high-quality humans in rapid motion with a hybrid frame-based RGB and bio-inspired event camera. The ``out-of-the-box'' insight is to leverage the high temporal information of event data in a complementary manner and adaptively reweight the effect of losses for both RGB frames and events in the local regions, according to the velocity of the rendered human. This significantly mitigates the inconsistency associated with motion blur in the RGB frames. Specifically, we first formulate a velocity field of the 3D body in the canonical space and render it to image space to identify the body parts with motion blur. We then propose two novel losses, i.e., velocity-aware photometric loss and velocity-relative event loss, to optimize the neural human for both modalities under the guidance of the estimated velocity. In addition, we incorporate novel pose regularization and alpha losses to facilitate continuous pose and clear boundary. Extensive experiments on synthetic and real-world datasets demonstrate that ExFMan can reconstruct sharper and higher quality humans.

Related papers

• Bundle Adjusted Gaussian Avatars Deblurring [31.718130377229482]
  We propose a 3D-aware, physics-oriented model of blur formation attributable to human movement and a 3D human motion model to clarify ambiguities found in motion-induced blurry images. We have established benchmarks for this task through a synthetic dataset derived from existing multi-view captures, alongside a real-captured dataset acquired through a 360-degree synchronous hybrid-exposure camera system.
  arXiv  Detail & Related papers  (2024-11-24T10:03:24Z)
• CRiM-GS: Continuous Rigid Motion-Aware Gaussian Splatting from Motion Blur Images [12.603775893040972]
  We propose continuous rigid motion-aware gaussian splatting (CRiM-GS) to reconstruct accurate 3D scene from blurry images with real-time rendering speed. We leverage rigid body transformations to model the camera motion with proper regularization, preserving the shape and size of the object. Furthermore, we introduce a continuous deformable 3D transformation in the textitSE(3) field to adapt the rigid body transformation to real-world problems.
  arXiv  Detail & Related papers  (2024-07-04T13:37:04Z)
• EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams [59.77837807004765]
  This paper introduces a new problem, i.e., 3D human motion capture from an egocentric monocular event camera with a fisheye lens. Event streams have high temporal resolution and provide reliable cues for 3D human motion capture under high-speed human motions and rapidly changing illumination. Our EE3D demonstrates robustness and superior 3D accuracy compared to existing solutions while supporting real-time 3D pose update rates of 140Hz.
  arXiv  Detail & Related papers  (2024-04-12T17:59:47Z)
• 3D Human Scan With A Moving Event Camera [7.734104968315144]
  Event cameras have the advantages of high temporal resolution and high dynamic range. This paper proposes a novel event-based method for 3D pose estimation and human mesh recovery.
  arXiv  Detail & Related papers  (2024-04-12T14:34:24Z)
• SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering [45.51684124904457]
  We propose a new 4D motion paradigm, SurMo, that models the temporal dynamics and human appearances in a unified framework. Surface-based motion encoding that models 4D human motions with an efficient compact surface-based triplane. Physical motion decoding that is designed to encourage physical motion learning. 4D appearance modeling that renders the motion triplanes into images by an efficient surface-conditioned decoding.
  arXiv  Detail & Related papers  (2024-04-01T16:34:27Z)
• NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields [99.57774680640581]
  We present an efficient framework capable of fast reconstruction, compact modeling, and streamable rendering. We propose to decompose the 4D space according to temporal characteristics. Points in the 4D space are associated with probabilities belonging to three categories: static, deforming, and new areas.
  arXiv  Detail & Related papers  (2022-10-28T07:11:05Z)
• Learning Motion Priors for 4D Human Body Capture in 3D Scenes [81.54377747405812]
  We propose LEMO: LEarning human MOtion priors for 4D human body capture. We introduce a novel motion prior, which reduces the jitters exhibited by poses recovered over a sequence. We also design a contact friction term and a contact-aware motion infiller obtained via per-instance self-supervised training. With our pipeline, we demonstrate high-quality 4D human body capture, reconstructing smooth motions and physically plausible body-scene interactions.
  arXiv  Detail & Related papers  (2021-08-23T20:47:09Z)
• Neural Monocular 3D Human Motion Capture with Physical Awareness [76.55971509794598]
  We present a new trainable system for physically plausible markerless 3D human motion capture. Unlike most neural methods for human motion capture, our approach is aware of physical and environmental constraints. It produces smooth and physically principled 3D motions in an interactive frame rate in a wide variety of challenging scenes.
  arXiv  Detail & Related papers  (2021-05-03T17:57:07Z)
• High-Fidelity Neural Human Motion Transfer from Monocular Video [71.75576402562247]
  Video-based human motion transfer creates video animations of humans following a source motion. We present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism.
  arXiv  Detail & Related papers  (2020-12-20T16:54:38Z)
• PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time [89.68248627276955]
  Marker-less 3D motion capture from a single colour camera has seen significant progress. However, it is a very challenging and severely ill-posed problem. We present PhysCap, the first algorithm for physically plausible, real-time and marker-less human 3D motion capture.
  arXiv  Detail & Related papers  (2020-08-20T10:46:32Z)

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.