Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing

• URL: http://arxiv.org/abs/2103.15432v1
• Date: Mon, 29 Mar 2021 08:58:10 GMT
• Title: Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing
• Authors: Abdallah Dib, Cedric Thebault, Junghyun Ahn, Philippe-Henri Gosselin, Christian Theobalt, Louis Chevallier
• Abstract summary: Methods combining deep neural network encoders with differentiable rendering have opened up the path for very fast monocular reconstruction of geometry, lighting and reflectance. ray tracing was introduced for monocular face reconstruction within a classic optimization-based framework. We propose a new method that greatly improves reconstruction quality and robustness in general scenes.
• Score: 49.759478460828504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust face reconstruction from monocular image in general lighting conditions is challenging. Methods combining deep neural network encoders with differentiable rendering have opened up the path for very fast monocular reconstruction of geometry, lighting and reflectance. They can also be trained in self-supervised manner for increased robustness and better generalization. However, their differentiable rasterization based image formation models, as well as underlying scene parameterization, limit them to Lambertian face reflectance and to poor shape details. More recently, ray tracing was introduced for monocular face reconstruction within a classic optimization-based framework and enables state-of-the art results. However optimization-based approaches are inherently slow and lack robustness. In this paper, we build our work on the aforementioned approaches and propose a new method that greatly improves reconstruction quality and robustness in general scenes. We achieve this by combining a CNN encoder with a differentiable ray tracer, which enables us to base the reconstruction on much more advanced personalized diffuse and specular albedos, a more sophisticated illumination model and a plausible representation of self-shadows. This enables to take a big leap forward in reconstruction quality of shape, appearance and lighting even in scenes with difficult illumination. With consistent face attributes reconstruction, our method leads to practical applications such as relighting and self-shadows removal. Compared to state-of-the-art methods, our results show improved accuracy and validity of the approach.

Related papers

• RelitLRM: Generative Relightable Radiance for Large Reconstruction Models [52.672706620003765]
  We propose RelitLRM for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations. Unlike prior inverse rendering methods requiring dense captures and slow optimization, RelitLRM adopts a feed-forward transformer-based model. We show our sparse-view feed-forward RelitLRM offers competitive relighting results to state-of-the-art dense-view optimization-based baselines.
  arXiv  Detail & Related papers  (2024-10-08T17:40:01Z)
• NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections [57.63028964831785]
  Recent works have improved NeRF's ability to render detailed specular appearance of distant environment illumination, but are unable to synthesize consistent reflections of closer content. We address these issues with an approach based on ray tracing. Instead of querying an expensive neural network for the outgoing view-dependent radiance at points along each camera ray, our model casts rays from these points and traces them through the NeRF representation to render feature vectors.
  arXiv  Detail & Related papers  (2024-05-23T17:59:57Z)
• GaNI: Global and Near Field Illumination Aware Neural Inverse Rendering [21.584362527926654]
  GaNI can reconstruct geometry, albedo, and roughness parameters from images of a scene captured with co-located light and camera. Existing inverse rendering techniques with co-located light-camera focus on single objects only.
  arXiv  Detail & Related papers  (2024-03-22T23:47:19Z)
• TensoIR: Tensorial Inverse Rendering [51.57268311847087]
  TensoIR is a novel inverse rendering approach based on tensor factorization and neural fields. TensoRF is a state-of-the-art approach for radiance field modeling.
  arXiv  Detail & Related papers  (2023-04-24T21:39:13Z)
• Geometry-aware Single-image Full-body Human Relighting [37.381122678376805]
  Single-image human relighting aims to relight a target human under new lighting conditions by decomposing the input image into albedo, shape and lighting. Previous methods suffer from both the entanglement between albedo and lighting and the lack of hard shadows. Our framework is able to generate photo-realistic high-frequency shadows such as cast shadows under challenging lighting conditions.
  arXiv  Detail & Related papers  (2022-07-11T10:21:02Z)
• Neural 3D Reconstruction in the Wild [86.6264706256377]
  We introduce a new method that enables efficient and accurate surface reconstruction from Internet photo collections. We present a new benchmark and protocol for evaluating reconstruction performance on such in-the-wild scenes.
  arXiv  Detail & Related papers  (2022-05-25T17:59:53Z)
• S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Image [2.469794902645761]
  We present a novel face reconstruction method capable of reconstructing detailed face geometry, spatially varying face reflectance from a single image. Compared to state-of-the-art methods, our method achieves more visually appealing reconstruction.
  arXiv  Detail & Related papers  (2022-03-15T08:55:45Z)
• DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer [78.91753256634453]
  We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiables. In this work, we propose DIBR++, a hybrid differentiable which supports these effects by combining specularization and ray-tracing. Compared to more advanced physics-based differentiables, DIBR++ is highly performant due to its compact and expressive model.
  arXiv  Detail & Related papers  (2021-10-30T01:59:39Z)
• Practical Face Reconstruction via Differentiable Ray Tracing [3.481486869779035]
  We present a differentiable ray-tracing based novel face reconstruction approach. Scene attributes - 3D geometry, reflectance (diffuse, specular and roughness), pose, camera parameters, and scene illumination - are estimated from unconstrained monocular images. We show the efficacy of our approach in several real-world scenarios, where face attributes can be estimated even under extreme illumination conditions.
  arXiv  Detail & Related papers  (2021-01-13T21:36:11Z)

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.