skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: End-to-End 3D Face Reconstruction with Expressions and Specular Albedos from Single In-the-wild Images
Recovering 3D face models from in-the-wild face images has numerous potential applications. However, properly modeling complex lighting effects in reality, including specular lighting, shadows, and occlusions, from a single in-the-wild face image is still considered as a widely open research challenge. In this paper, we propose a convolutional neural network based framework to regress the face model from a single image in the wild. The outputted face model includes dense 3D shape, head pose, expression, diffuse albedo, specular albedo, and the corresponding lighting conditions. Our approach uses novel hybrid loss functions to disentangle face shape identities, expressions, poses, albedos, and lighting. Besides a carefully designed ablation study, we also conduct direct comparison experiments to show that our method can outperform state-of-art methods both quantitatively and qualitatively.  more » « less
Award ID(s):
2005430
PAR ID:
10463606
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Proceeding of ACM International Conference on Multimedia 2022
Page Range / eLocation ID:
4694 to 4703
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, International Conference on Computational Photography)
    Reconstructing 3D objects in natural environments requires solving the ill-posed problem of geometry, spatially-varying material, and lighting estimation. As such, many approaches impractically constrain to a dark environment, use controlled lighting rigs, or use few handheld captures but suffer reduced quality. We develop a method that uses just two smartphone exposures captured in ambient lighting to reconstruct appearance more accurately and practically than baseline methods. Our insight is that we can use a flash/no-flash RGB-D pair to pose an inverse rendering problem using point lighting. This allows efficient differentiable rendering to optimize depth and normals from a good initialization and so also the simultaneous optimization of diffuse environment illumination and SVBRDF material. We find that this reduces diffuse albedo error by 25%, specular error by 46%, and normal error by 30% against single and paired-image baselines that use learning-based techniques. Given that our approach is practical for everyday solid objects, we enable photorealistic relighting for mobile photography and easier content creation for augmented reality. 
    more » « less
  2. ; ; ; (, 3DV)
    Recent work on 3D-aware image synthesis has achieved compelling results using advances in neural rendering. However, 3D-aware synthesis of face dynamics hasn't received much attention. Here, we study how to explicitly control generative model synthesis of face dynamics exhibiting non-rigid motion (e.g., facial expression change), while simultaneously ensuring 3D-awareness. For this we propose a Controllable Radiance Field (CoRF): 1) Motion control is achieved by embedding motion features within the layered latent motion space of a style-based generator; 2) To ensure consistency of background, motion features and subject-specific attributes such as lighting, texture, shapes, albedo, and identity, a face parsing net, a head regressor and an identity encoder are incorporated. On head image/video data we show that CoRFs are 3D-aware while enabling editing of identity, viewing directions, and motion. 
    more » « less
  3. ; ; ; (, Biomedical Optics Express)
    Camera-based heart rate measurement is becoming an attractive option as a non-contact modality for continuous remote health and engagement monitoring. However, reliable heart rate extraction from camera-based measurement is challenging in realistic scenarios, especially when the subject is moving. In this work, we develop a motion-robust algorithm, labeled RobustPPG, for extracting photoplethysmography signals (PPG) from face video and estimating the heart rate. Our key innovation is to explicitly model and generate motion distortions due to the movements of the person’s face. We use inverse rendering to obtain the 3D shape and albedo of the face and environment lighting from video frames and then render the human face for each frame. The rendered face is similar to the original face but does not contain the heart rate signal; facial movements alone cause pixel intensity variation in the generated video frames. Finally, we use the generated motion distortion to filter the motion-induced measurements. We demonstrate that our approach performs better than the state-of-the-art methods in extracting a clean blood volume signal with over 2 dB signal quality improvement and 30% improvement in RMSE of estimated heart rate in intense motion scenarios. 
    more » « less
  4. ; ; ; ; (, Springer Nature Switzerland)
    Prior works for reconstructing hand-held objects from a single image train models on images paired with 3D shapes. Such data is challenging to gather in the real world at scale. Consequently, these approaches do not generalize well when presented with novel objects in in-the-wild settings. While 3D supervision is a major bottleneck, there is an abundance of a) in-the-wild raw video data showing hand-object interactions and b) synthetic 3D shape collections. In this paper, we propose modules to leverage 3D supervision from these sources to scale up the learning of models for reconstructing hand-held objects. Specifically, we extract multiview 2D mask supervision from videos and 3D shape priors from shape collections. We use these indirect 3D cues to train occupancy networks that predict the 3D shape of objects from a single RGB image. Our experiments in the challenging object generalization setting on in-the-wild MOW dataset show 11.6% relative improvement over models trained with 3D supervision on existing datasets. 
    more » « less
  5. ; ; ; ; (, Springer Nature Switzerland)
    Prior works for reconstructing hand-held objects from a single image train models on images paired with 3D shapes. Such data is challenging to gather in the real world at scale. Consequently, these approaches do not generalize well when presented with novel objects in in-the-wild settings. While 3D supervision is a major bottleneck, there is an abundance of a) in-the-wild raw video data showing hand-object interactions and b) synthetic 3D shape collections. In this paper, we propose modules to leverage 3D supervision from these sources to scale up the learning of models for reconstructing hand-held objects. Specifically, we extract multiview 2D mask supervision from videos and 3D shape priors from shape collections. We use these indirect 3D cues to train occupancy networks that predict the 3D shape of objects from a single RGB image. Our experiments in the challenging object generalization setting on in-the-wild MOW dataset show 11.6% relative improvement over models trained with 3D supervision on existing datasets. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email