We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields involves optimizing the representation to every scene independently, requiring many calibrated views and significant compute time. We take a step towards resolving these shortcomings by introducing an architecture that conditions a NeRF on image inputs in a fully convolutional manner. This allows the network to be trained across multiple scenes to learn a scene prior, enabling it to perform novel view synthesis in a feed-forward manner from a sparse set of views (as few as one). Leveraging the volume rendering approach of NeRF, our model can be trained directly from images with no explicit 3D supervision. We conduct extensive experiments on ShapeNet benchmarks for single image novel view synthesis tasks with held-out objects as well as entire unseen categories. We further demonstrate the flexibility of pixelNeRF by demonstrating it on multi-object ShapeNet scenes and real scenes from the DTU dataset. In all cases, pixelNeRF outperforms current state-of-the-art baselines for novel view synthesis and single image 3D reconstruction. For the video and code, please visit the project website: this https URL

pixelNeRF: Neural Radiance Fields from One or Few Images

While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, e.g., the object identity may vary with the viewpoint. In this paper, we propose a generative model for radiance fields which have recently proven successful for novel view synthesis of a single scene. In contrast to voxel-based representations, radiance fields are not confined to a coarse discretization of the 3D space, yet allow for disentangling camera and scene properties while degrading gracefully in the presence of reconstruction ambiguity. By introducing a multi-scale patch-based discriminator, we demonstrate synthesis of high-resolution images while training our model from unposed 2D images alone. We systematically analyze our approach on several challenging synthetic and real-world datasets. Our experiments reveal that radiance fields are a powerful representation for generative image synthesis, leading to 3D consistent models that render with high fidelity.

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

View synthesis allows for the generation of new views of a scene given one or more images. This is challenging; it requires comprehensively understanding the 3D scene from images. As a result, current methods typically use multiple images, train on ground-truth depth, or are limited to synthetic data. We propose a novel end-to-end model for this task using a single image at test time; it is trained on real images without any ground-truth 3D information. To this end, we introduce a novel differentiable point cloud renderer that is used to transform a latent 3D point cloud of features into the target view. The projected features are decoded by our refinement network to inpaint missing regions and generate a realistic output image. The 3D component inside of our generative model allows for interpretable manipulation of the latent feature space at test time, e.g. we can animate trajectories from a single image. Additionally, we can generate high resolution images and generalise to other input resolutions. We outperform baselines and prior work on the Matterport, Replica, and RealEstate10K datasets.

/pdf/synsin-end-to-end-view-synthesis-from-a-single-image-262cndeeze.pdf

SynSin: End-to-End View Synthesis From a Single Image

We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields [27] involves optimizing the representation to every scene independently, requiring many calibrated views and significant compute time. We take a step towards resolving these shortcomings by introducing an architecture that conditions a NeRF on image inputs in a fully convolutional manner. This allows the network to be trained across multiple scenes to learn a scene prior, enabling it to perform novel view synthesis in a feed-forward manner from a sparse set of views (as few as one). Leveraging the volume rendering approach of NeRF, our model can be trained directly from images with no explicit 3D supervision. We conduct extensive experiments on ShapeNet benchmarks for single image novel view synthesis tasks with held-out objects as well as entire unseen categories. We further demonstrate the flexibility of pixelNeRF by demonstrating it on multi-object ShapeNet scenes and real scenes from the DTU dataset. In all cases, pixelNeRF outperforms current state-of-the-art baselines for novel view synthesis and single image 3D reconstruction. For the video and code, please visit the project website:https://alexyu.net/pixelnerf.

/pdf/pixelnerf-neural-radiance-fields-from-one-or-few-images-3v3w0a3sz5.pdf

We present iNeRF, a framework that performs mesh-free pose estimation by "inverting" a Neural RadianceField (NeRF). NeRFs have been shown to be remarkably effective for the task of view synthesis - synthesizing photorealistic novel views of real-world scenes or objects. In this work, we investigate whether we can apply analysis-by-synthesis via NeRF for mesh-free, RGB-only 6DoF pose estimation - given an image, find the translation and rotation of a camera relative to a 3D object or scene. Our method assumes that no object mesh models are available during either training or test time. Starting from an initial pose estimate, we use gradient descent to minimize the residual between pixels rendered from a NeRF and pixels in an observed image. In our experiments, we first study 1) how to sample rays during pose refinement for iNeRF to collect informative gradients and 2) how different batch sizes of rays affect iNeRF on a synthetic dataset. We then show that for complex real-world scenes from the LLFF dataset, iNeRF can improve NeRF by estimating the camera poses of novel images and using these images as additional training data for NeRF. Finally, we show iNeRF can perform category-level object pose estimation, including object instances not seen during training, with RGB images by inverting a NeRF model inferred from a single view.

iNeRF: Inverting Neural Radiance Fields for Pose Estimation

Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances. In this paper we combine a gradient-based fitting procedure with a parametric neural image synthesis module that is capable of implicitly representing the appearance, shape and pose of entire object categories, thus rendering the need for explicit CAD models per object instance unnecessary. The image synthesis network is designed to efficiently span the pose configuration space so that model capacity can be used to capture the shape and local appearance (i.e., texture) variations jointly. At inference time the synthesized images are compared to the target via an appearance based loss and the error signal is backpropagated through the network to the input parameters. Keeping the network parameters fixed, this allows for iterative optimization of the object pose, shape and appearance in a joint manner and we experimentally show that the method can recover orientation of objects with high accuracy from 2D images alone. When provided with depth measurements, to overcome scale ambiguities, the method can accurately recover the full 6DOF pose successfully.

Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

We propose a method to produce a continuous stream of novel views under fine-grained (e.g., 1 degree step-size) camera control at interactive rates. A novel learning pipeline determines the output pixels directly from the source color. Injecting geometric transformations, including perspective projection, 3D rotation and translation into the network forces implicit reasoning about the underlying geometry. The latent 3D geometry representation is compact and meaningful under 3D transformation, being able to produce geometrically accurate views for both single objects and natural scenes. Our experiments show that both proposed components, the transforming encoder-decoder and depth-guided appearance mapping, lead to significantly improved generalization beyond the training views and in consequence to more accurate view synthesis under continuous 6-DoF camera control. Finally, we show that our method outperforms state-of-the-art baseline methods on public datasets.

/pdf/monocular-neural-image-based-rendering-with-continuous-view-1v1izjybgy.pdf

Monocular Neural Image Based Rendering With Continuous View Control

We present an approach that learns to synthesize high-quality, novel views of 3D objects or scenes, while providing fine-grained and precise control over the 6-DOF viewpoint. The approach is self-supervised and only requires 2D images and associated view transforms for training. Our main contribution is a network architecture that leverages a transforming auto-encoder in combination with a depth-guided warping procedure to predict geometrically accurate unseen views. Leveraging geometric constraints renders direct supervision via depth or flow maps unnecessary. If large parts of the object are occluded in the source view, a purely learning based prior is used to predict the values for dis-occluded pixels. Our network furthermore predicts a per-pixel mask, used to fuse depth-guided and pixel-based predictions. The resulting images reflect the desired 6-DOF transformation and details are preserved. We thoroughly evaluate our architecture on synthetic and real scenes and under fine-grained and fixed-view settings. Finally, we demonstrate that the approach generalizes to entirely unseen images such as product images downloaded from the internet.

Monocular Neural Image Based Rendering with Continuous View Control

We propose a novel algorithm for the fitting of 3D human shape to images. Combining the accuracy and refinement capabilities of iterative gradient-based optimization techniques with the robustness of deep neural networks, we propose a gradient descent algorithm that leverages a neural network to predict the parameter update rule for each iteration. This per-parameter and state-aware update guides the optimizer towards a good solution in very few steps, converging in typically few steps. During training our approach only requires MoCap data of human poses, parametrized via SMPL. From this data the network learns a subspace of valid poses and shapes in which optimization is performed much more efficiently. The approach does not require any hard to acquire image-to-3D correspondences. At test time we only optimize the 2D joint re-projection error without the need for any further priors or regularization terms. We show empirically that this algorithm is fast (avg. 120ms convergence), robust to initialization and dataset, and achieves state-of-the-art results on public evaluation datasets including the challenging 3DPW in-the-wild benchmark (improvement over SMPLify (\(45\%\)) and also approaches using image-to-3D correspondences).

Human Body Model Fitting by Learned Gradient Descent

Neural implicit surface representations have emerged as a promising paradigm to capture 3D shapes in a continuous and resolution-independent manner. However, adapting them to articulated shapes is non-trivial. Existing approaches learn a backward warp field that maps deformed to canonical points. However, this is problematic since the backward warp field is pose dependent and thus requires large amounts of data to learn. To address this, we introduce SNARF, which combines the advantages of linear blend skinning (LBS) for polygonal meshes with those of neural implicit surfaces by learning a forward deformation field without direct supervision. This deformation field is defined in canonical, pose-independent space, allowing for generalization to unseen poses. Learning the deformation field from posed meshes alone is challenging since the correspondences of deformed points are defined implicitly and may not be unique under changes of topology. We propose a forward skinning model that finds all canonical correspondences of any deformed point using iterative root finding. We derive analytical gradients via implicit differentiation, enabling end-to-end training from 3D meshes with bone transformations. Compared to state-of-the-art neural implicit representations, our approach generalizes better to unseen poses while preserving accuracy. We demonstrate our method in challenging scenarios on (clothed) 3D humans in diverse and unseen poses.

/pdf/snarf-differentiable-forward-skinning-for-animating-non-4uzcpg2ag2.pdf

Xu Chen

Papers

Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

Monocular Neural Image Based Rendering With Continuous View Control

Monocular Neural Image Based Rendering with Continuous View Control

Human Body Model Fitting by Learned Gradient Descent

SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes