2022-06-13 更新
From data to functa: Your data point is a function and you can treat it like one
Authors:Emilien Dupont, Hyunjik Kim, S. M. Ali Eslami, Danilo Rezende, Dan Rosenbaum
It is common practice in deep learning to represent a measurement of the world on a discrete grid, e.g. a 2D grid of pixels. However, the underlying signal represented by these measurements is often continuous, e.g. the scene depicted in an image. A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location. In this paper, we take this idea to its next level: what would it take to perform deep learning on these functions instead, treating them as data? In this context we refer to the data as functa, and propose a framework for deep learning on functa. This view presents a number of challenges around efficient conversion from data to functa, compact representation of functa, and effectively solving downstream tasks on functa. We outline a recipe to overcome these challenges and apply it to a wide range of data modalities including images, 3D shapes, neural radiance fields (NeRF) and data on manifolds. We demonstrate that this approach has various compelling properties across data modalities, in particular on the canonical tasks of generative modeling, data imputation, novel view synthesis and classification.
PDF
论文截图
NeRF-In: Free-Form NeRF Inpainting with RGB-D Priors
Authors:Hao-Kang Liu, I-Chao Shen, Bing-Yu Chen
Though Neural Radiance Field (NeRF) demonstrates compelling novel view synthesis results, it is still unintuitive to edit a pre-trained NeRF because the neural network’s parameters and the scene geometry/appearance are often not explicitly associated. In this paper, we introduce the first framework that enables users to remove unwanted objects or retouch undesired regions in a 3D scene represented by a pre-trained NeRF without any category-specific data and training. The user first draws a free-form mask to specify a region containing unwanted objects over a rendered view from the pre-trained NeRF. Our framework first transfers the user-provided mask to other rendered views and estimates guiding color and depth images within these transferred masked regions. Next, we formulate an optimization problem that jointly inpaints the image content in all masked regions across multiple views by updating the NeRF model’s parameters. We demonstrate our framework on diverse scenes and show it obtained visual plausible and structurally consistent results across multiple views using shorter time and less user manual efforts.
PDF Hao-Kang Liu and I-Chao Shen contributed equally to the paper. Project page: https://jdily.github.io/proj_site/nerfin_proj.html
论文截图
Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields
Authors:Mingtong Zhang, Shuhong Zheng, Zhipeng Bao, Martial Hebert, Yu-Xiong Wang
Comprehensive 3D scene understanding, both geometrically and semantically, is important for real-world applications such as robot perception. Most of the existing work has focused on developing data-driven discriminative models for scene understanding. This paper provides a new approach to scene understanding, from a synthesis model perspective, by leveraging the recent progress on implicit 3D representation and neural rendering. Building upon the great success of Neural Radiance Fields (NeRFs), we introduce Scene-Property Synthesis with NeRF (SS-NeRF) that is able to not only render photo-realistic RGB images from novel viewpoints, but also render various accurate scene properties (e.g., appearance, geometry, and semantics). By doing so, we facilitate addressing a variety of scene understanding tasks under a unified framework, including semantic segmentation, surface normal estimation, reshading, keypoint detection, and edge detection. Our SS-NeRF framework can be a powerful tool for bridging generative learning and discriminative learning, and thus be beneficial to the investigation of a wide range of interesting problems, such as studying task relationships within a synthesis paradigm, transferring knowledge to novel tasks, facilitating downstream discriminative tasks as ways of data augmentation, and serving as auto-labeller for data creation.
PDF
论文截图
Differentiable Point-Based Radiance Fields for Efficient View Synthesis
Authors:Qiang Zhang, Seung-Hwan Baek, Szymon Rusinkiewicz, Felix Heide
We propose a differentiable rendering algorithm for efficient novel view synthesis. By departing from volume-based representations in favor of a learned point representation, we improve on existing methods more than an order of magnitude in memory and runtime, both in training and inference. The method begins with a uniformly-sampled random point cloud and learns per-point position and view-dependent appearance, using a differentiable splat-based renderer to evolve the model to match a set of input images. Our method is up to 300x faster than NeRF in both training and inference, with only a marginal sacrifice in quality, while using less than 10~MB of memory for a static scene. For dynamic scenes, our method trains two orders of magnitude faster than STNeRF and renders at near interactive rate, while maintaining high image quality and temporal coherence even without imposing any temporal-coherency regularizers.
PDF
论文截图
Points2NeRF: Generating Neural Radiance Fields from 3D point cloud
Authors:D. Zimny, T. Trzciński, P. Spurek
Contemporary registration devices for 3D visual information, such as LIDARs and various depth cameras, capture data as 3D point clouds. In turn, such clouds are challenging to be processed due to their size and complexity. Existing methods address this problem by fitting a mesh to the point cloud and rendering it instead. This approach, however, leads to the reduced fidelity of the resulting visualization and misses color information of the objects crucial in computer graphics applications. In this work, we propose to mitigate this challenge by representing 3D objects as Neural Radiance Fields (NeRFs). We leverage a hypernetwork paradigm and train the model to take a 3D point cloud with the associated color values and return a NeRF network’s weights that reconstruct 3D objects from input 2D images. Our method provides efficient 3D object representation and offers several advantages over the existing approaches, including the ability to condition NeRFs and improved generalization beyond objects seen in training. The latter we also confirmed in the results of our empirical evaluation.
PDF arXiv admin note: text overlap with arXiv:2003.08934 by other authors
论文截图
Mip-NeRF RGB-D: Depth Assisted Fast Neural Radiance Fields
Authors:Arnab Dey, Yassine Ahmine, Andrew I. Comport
Neural scene representations, such as Neural Radiance Fields (NeRF), are based on training a multilayer perceptron (MLP) using a set of color images with known poses. An increasing number of devices now produce RGB-D(color + depth) information, which has been shown to be very important for a wide range of tasks. Therefore, the aim of this paper is to investigate what improvements can be made to these promising implicit representations by incorporating depth information with the color images. In particular, the recently proposed Mip-NeRF approach, which uses conical frustums instead of rays for volume rendering, allows one to account for the varying area of a pixel with distance from the camera center. The proposed method additionally models depth uncertainty. This allows to address major limitations of NeRF-based approaches including improving the accuracy of geometry, reduced artifacts, faster training time, and shortened prediction time. Experiments are performed on well-known benchmark scenes, and comparisons show improved accuracy in scene geometry and photometric reconstruction, while reducing the training time by 3 - 5 times.
PDF
论文截图
Neural Point Light Fields
Authors:Julian Ost, Issam Laradji, Alejandro Newell, Yuval Bahat, Felix Heide
We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud. Combining differentiable volume rendering with learned implicit density representations has made it possible to synthesize photo-realistic images for novel views of small scenes. As neural volumetric rendering methods require dense sampling of the underlying functional scene representation, at hundreds of samples along a ray cast through the volume, they are fundamentally limited to small scenes with the same objects projected to hundreds of training views. Promoting sparse point clouds to neural implicit light fields allows us to represent large scenes effectively with only a single radiance evaluation per ray. These point light fields are a function of the ray direction, and local point feature neighborhood, allowing us to interpolate the light field conditioned training images without dense object coverage and parallax. We assess the proposed method for novel view synthesis on large driving scenarios, where we synthesize realistic unseen views that existing implicit approaches fail to represent. We validate that Neural Point Light Fields make it possible to predict videos along unseen trajectories previously only feasible to generate by explicitly modeling the scene.
PDF 9 pages, replacement changed font of equations
论文截图