Reconstructing the geometry and appearance of objects from photographs taken in different environments is difficult as the illumination and, therefore, the object appearance vary across captured images. This is particularly challenging for specular objects whose appearance strongly depends on the viewing direction. Some prior approaches model appearance variation across images using a per-image embedding vector, while others use physically-based rendering to recover the materials and per-image illumination. Such approaches fail at faithfully recovering view-dependent appearance given the significant variation in input illumination and tend to produce mostly diffuse results. We present an approach that reconstructs objects from images taken under different illuminations by first relighting the images under a single reference illumination with a multiview relighting diffusion model and then reconstructing the object’s geometry and appearance with a radiance field architecture that is robust to the minor remaining inconsistencies among the relit images. We validate our approach on synthetic and real datasets and demonstrate that it outperforms existing techniques at reconstructing high-fidelity appearance from images taken under extreme illumination variation. Moreover, our approach is particularly effective at recovering view-dependent "shiny" appearance which cannot be reconstructed by prior methods.

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are difficult to model explicitly. We present an approach for leveraging generative video models to simulate the inconsistencies in the world that can occur during capture. We use this process, along with existing multi-view datasets, to create synthetic data for training a multi-view harmonization network that is able to reconcile inconsistent observations into a consistent 3D scene. We demonstrate that our world-simulation strategy significantly outperforms traditional augmentation methods in handling real-world scene variations, thereby enabling highly accurate static 3D reconstructions in the presence of a variety of challenging inconsistencies. Project page: https://alextrevithick.com/simvs

Weak gravitational lensing is the slight distortion of galaxy shapes caused primarily by the gravitational effects of dark matter in the universe. In our work, we seek to invert the weak lensing signal from 2D telescope images to reconstruct a 3D map of the universe's dark matter field. While inversion typically yields a 2D projection of the dark matter field, accurate 3D maps of the dark matter distribution are essential for localizing structures of interest and testing theories of our universe. However, 3D inversion poses significant challenges. First, unlike standard 3D reconstruction that relies on multiple viewpoints, in this case, images are only observed from a single viewpoint. This challenge can be partially addressed by observing how galaxy emitters throughout the volume are lensed. However, this leads to the second challenge: the shapes and exact locations of unlensed galaxies are unknown, and can only be estimated with a very large degree of uncertainty. This introduces an overwhelming amount of noise which nearly drowns out the lensing signal completely. Previous approaches tackle this by imposing strong assumptions about the structures in the volume. We instead propose a methodology using a gravitationally-constrained neural field to flexibly model the continuous matter distribution. We take an analysis-by-synthesis approach, optimizing the weights of the neural network through a fully differentiable physical forward model to reproduce the lensing signal present in image measurements. We showcase our method on simulations, including realistic simulated measurements of dark matter distributions that mimic data from upcoming telescope surveys. Our results show that our method can not only outperform previous methods, but importantly is also able to recover potentially surprising dark matter structures.

We introduce ROGR, a novel approach that reconstructs a relightable 3D model of an object captured from multiple views, driven by a generative relighting model that simulates the effects of placing the object under novel environment illuminations. Our method samples the appearance of the object under multiple lighting environments, creating a dataset that is used to train a lighting-conditioned Neural Radiance Field (NeRF) that outputs the object's appearance under any input environmental lighting. The lighting-conditioned NeRF uses a novel dual-branch architecture to encode the general lighting effects and specularities separately. The optimized lighting-conditioned NeRF enables efficient feed-forward relighting under arbitrary environment maps without requiring per-illumination optimization or light transport simulation. We evaluate our approach on the established TensoIR and Stanford-ORB datasets, where it improves upon the state-of-the-art on most metrics, and showcase our approach on real-world object captures.

Neural volumetric representations such as Neural Radiance Fields (NeRF) have emerged as a compelling technique for learning to represent 3D scenes from images with the goal of rendering photorealistic images of the scene from unobserved viewpoints. However, NeRF's computational requirements are prohibitive for real-time applications: rendering views from a trained NeRF requires querying a multilayer perceptron (MLP) hundreds of times per ray. We present a method to train a NeRF, then precompute and store (i.e., "bake") it as a novel representation called a Sparse Neural Radiance Grid (SNeRG) that enables real-time rendering on commodity hardware. To achieve this, we introduce 1) a reformulation of NeRF's architecture and 2) a sparse voxel grid representation with learned feature vectors. The resulting scene representation retains NeRF's ability to render fine geometric details and view-dependent appearance, is compact (averaging less than 90 MB per scene), and can be rendered in real-time (higher than 30 frames per second on a laptop GPU). Actual screen captures are shown in our video.

Neural Radiance Fields (NeRF) is a popular view synthesis technique that represents a scene as a continuous volumetric function, parameterized by multilayer perceptrons that provide the volume density and view-dependent emitted radiance at each location. While NeRF-based techniques excel at representing fine geometric structures with smoothly varying view-dependent appearance, they often fail to accurately capture and reproduce the appearance of glossy surfaces. We address this limitation by introducing Ref-NeRF, which replaces NeRF's parameterization of view-dependent outgoing radiance with a representation of reflected radiance and structures this function using a collection of spatially-varying scene properties. We show that together with a regularizer on normal vectors, our model significantly improves the realism and accuracy of specular reflections. Furthermore, we show that our model's internal representation of outgoing radiance is interpretable and useful for scene editing.

Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known before-hand. This problem is especially challenging for diffuse objects: it is ill-conditioned because diffuse materials severely blur incoming light, and it is ill-posed because diffuse materials under high-frequency lighting can be indistinguishable from shiny materials under low-frequency lighting. We show that it is possible to recover precise materials and illumination-even from diffuse objects-by exploiting un-intended shadows, like the ones cast onto an object by the photographer who moves around it. These shadows are a nuisance in most previous inverse rendering pipelines, but here we exploit them as signals that improve conditioning and help resolve material-lighting ambiguities. We present a method based on differentiable Monte Carlo ray tracing that uses images of an object to jointly recover its spatially-varying materials, the surrounding illumination environment, and the shapes of the unseen light occluders who in-advertently cast shadows upon it.

We present a method that uses a text-to-image model to generate consistent content across multiple image scales, enabling extreme semantic zooms into a scene, e.g. ranging from a wide-angle landscape view of a forest to a macro shot of an insect sitting on one of the tree branches. We achieve this through a joint multi-scale diffusion sampling approach that encourages consistency across different scales while preserving the integrity of each individual sampling process. Since each generated scale is guided by a different text prompt, our method enables deeper levels of zoom than traditional super-resolution methods that may struggle to create new contextual structure at vastly different scales. We compare our method qualitatively with alter-native techniques in image super-resolution and outpainting, and show that our method is most effective at generating consistent multi-scale content.

3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes. However, recovering a high-quality NeRF typically requires tens to hundreds of input images, resulting in a time-consuming capture process. We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis, trained on synthetic and multiview datasets, which regularizes a NeRF-based 3D reconstruction pipeline at novel camera poses beyond those captured by the set of input images. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions. We perform an extensive evaluation across various real-world datasets, including forward-facing and 360-degree scenes, demonstrating significant performance improvements over previous few-view NeRF reconstruction approaches. Please see our project page at reconfusion.github. io.

Refractive Index Tomography is the inverse problem of reconstructing the continuously-varying 3D refractive in-dex in a scene using 2D projected image measurements. Although a purely refractive field is not directly visible, it bends light rays as they travel through space, thus providing a signal for reconstruction. The effects of such fields appear in many scientific computer vision settings, ranging from refraction due to transparent cells in microscopy to the lensing of distant galaxies caused by dark matter in astro-physics. Reconstructing these fields is particularly difficult due to the complex nonlinear effects of the refractive field on observed images. Furthermore, while standard 3D reconstruction and tomography settings typically have access to observations of the scene from many viewpoints, many refractive index tomography problem settings only have access to images observed from a single viewpoint. We in-troduce a method that leverages prior knowledge of light sources scattered throughout the refractive medium to help disambiguate the single-view refractive index tomography problem. We differentiably trace curved rays through a neural field representation of the refractive field, and optimize its parameters to best reproduce the observed image. We demonstrate the efficacy of our approach by reconstructing simulated refractive fields, analyze the effects of light source distribution on the recovered field, and test our method on a simulated dark matter mapping problem where we successfully recover the 3D refractive field caused by a realistic dark matter distribution.

Advances in 3D reconstruction have enabled high-quality 3D capture, but require a user to collect hundreds to thousands of images to create a 3D scene. We present CAT3D, a method for creating anything in 3D by simulating this real-world capture process with a multi-view diffusion model. Given any number of input images and a set of target novel viewpoints, our model generates highly consistent novel views of a scene. These generated views can be used as input to robust 3D reconstruction techniques to produce 3D representations that can be rendered from any viewpoint in real-time. CAT3D can create entire 3D scenes in as little as one minute, and outperforms existing methods for single image and few-view 3D scene creation.

Existing methods for relightable view synthesis --- using a set of images of an object under unknown lighting to recover a 3D representation that can be rendered from novel viewpoints under a target illumination --- are based on inverse rendering, and attempt to disentangle the object geometry, materials, and lighting that explain the input images. Furthermore, this typically involves optimization through differentiable Monte Carlo rendering, which is brittle and computationally-expensive. In this work, we propose a simpler approach: we first relight each input image using an image diffusion model conditioned on target environment lighting and estimated object geometry. We then reconstruct a Neural Radiance Field (NeRF) with these relit images, from which we render novel views under the target lighting. We demonstrate that this strategy is surprisingly competitive and achieves state-of-the-art results on multiple relighting benchmarks. Please see our project page at [illuminerf.github.io](illuminerf.github.io).

While surface-based view synthesis algorithms are appealing due to their low computational requirements, they often struggle to reproduce thin structures. In contrast, more expensive methods that model the scene's geometry as a volumetric density field (e.g. NeRF) excel at reconstructing fine geometric detail. However, density fields often represent geometry in a "fuzzy" manner, which hinders exact localization of the surface. In this work, we modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. First, we employ a discrete opacity grid representation instead of a continuous density field, which allows opacity values to discontinuously transition from zero to one at the surface. Second, we anti-alias by casting multiple rays per pixel, which allows occlusion boundaries and subpixel structures to be modelled without using semi-transparent voxels. Third, we minimize the binary entropy of the opacity values, which facilitates the extraction of surface geometry by encouraging opacity values to binarize towards the end of training. Lastly, we develop a fusion-based meshing strategy followed by mesh simplification and appearance model fitting. The compact meshes produced by our model can be rendered in real-time on mobile devices and achieve significantly higher view synthesis quality compared to existing mesh-based approaches. Our interactive webdemo is available at https://binary-opacity-grid.github.io.

We present PersonNeRF, a method that takes a collection of photos of a subject (e.g. Roger Federer) captured across multiple years with arbitrary body poses and ap-pearances, and enables rendering the subject with arbitrary novel combinations of viewpoint, body pose, and appearance. PersonNeRF builds a customized neural volumetric 3D model of the subject that is able to render an entire space spanned by camera viewpoint, body pose, and appearance. A central challenge in this task is dealing with sparse observations; a given body pose is likely only observed by a single viewpoint with a single appearance, and a given appearance is only observed under a handful of different body poses. We address this issue by recovering a canonical T-pose neural volumetric representation of the subject that allows for changing appearance across different observations, but uses a shared pose-dependent motion field across all observations. We demonstrate that this approach, along with regularization of the recovered volumetric geometry to encourage smoothness, is able to recover a model that renders compelling images from novel combinations of viewpoint, pose, and appearance from these challenging unstructured photo collections, outperforming prior work for free-viewpoint human rendering.

Neural Radiance Field training can be accelerated through the use of grid-based representations in NeRF’s learned mapping from spatial coordinates to colors and volumetric density. However, these grid-based approaches lack an explicit understanding of scale and therefore often introduce aliasing, usually in the form of jaggies or missing scene content. Anti-aliasing has previously been addressed by mip-NeRF 360, which reasons about sub-volumes along a cone rather than points along a ray, but this approach is not natively compatible with current grid-based techniques. We show how ideas from rendering and signal processing can be used to construct a technique that combines mip-NeRF 360 and grid-based models such as Instant NGP to yield error rates that are 8% – 77% lower than either prior technique, and that trains 24× faster than mip-NeRF 360.

Recent work has shown the possibility of training generative models of 3D content from 2D image collections on small datasets corresponding to a single object class, such as human faces, animal faces, or cars. However, these models struggle on larger, more complex datasets. To model diverse and unconstrained image collections such as ImageNet, we present VQ3D, which introduces a NeRF-based decoder into a two-stage vector-quantized autoencoder. Our Stage 1 allows for the reconstruction of an input image and the ability to change the camera position around the image, and our Stage 2 allows for the generation of new 3D scenes. VQ3D is capable of generating and reconstructing 3D-aware images from the 1000-class ImageNet dataset of 1.2 million training images, and achieves a competitive ImageNet generation FID score of 16.8. Our project webpage is at this url.

Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale to large scenes. We present a Memory-Efficient Radiance Field (MERF) representation that achieves real-time rendering of large-scale scenes in a browser. MERF reduces the memory consumption of prior sparse volumetric radiance fields using a combination of a sparse feature grid and high-resolution 2D feature planes. To support large-scale unbounded scenes, we introduce a novel contraction function that maps scene coordinates into a bounded volume while still allowing for efficient ray-box intersection. We design a lossless procedure for baking the parameterization used during training into a model that achieves real-time rendering while still preserving the photorealistic view synthesis quality of a volumetric radiance field.

Though neural radiance fields (NeRF) have demon-strated impressive view synthesis results on objects and small bounded regions of space, they struggle on “un-bounded” scenes, where the camera may point in any di-rection and content may exist at any distance. In this set-ting, existing NeRF-like models often produce blurry or low-resolution renderings (due to the unbalanced detail and scale of nearby and distant objects), are slow to train, and may exhibit artifacts due to the inherent ambiguity of the task of reconstructing a large scene from a small set of images. We present an extension of mip-NeRF (a NeRF variant that addresses sampling and aliasing) that uses a non-linear scene parameterization, online distillation, and a novel distortion-based regularizer to overcome the chal-lenges presented by unbounded scenes. Our model, which we dub “mip-NeRF 360” as we target scenes in which the camera rotates 360 degrees around a point, reduces mean-squared error by 57% compared to mip-NeRF, and is able to produce realistic synthesized views and detailed depth maps for highly intricate, unbounded real-world scenes.

Measurements from the Event Horizon Telescope enabled the visualization of light emission around a black hole for the first time. So far, these measurements have been used to recover a 2D image under the assumption that the emission field is static over the period of acquisition. In this work, we propose BH-NeRF, a novel tomography approach that leverages gravitational lensing to recover the continuous 3D emission field near a black hole. Compared to other 3D reconstruction or tomography settings, this task poses two significant challenges: first, rays near black holes follow curved paths dictated by general relativity, and second, we only observe measurements from a single viewpoint. Our method captures the unknown emission field using a continuous volumetric function parameterized by a coordinate-based neural network, and uses knowledge of Keplerian orbital dynamics to establish correspondence between 3D points over time. Together, these enable BHNeRF to recover accurate 3D emission fields, even in challenging situations with sparse measurements and uncertain orbital dynamics. This work takes the first steps in showing how future measurements from the Event Horizon Telescope could be used to recover evolving 3D emission around the supermassive black hole in our Galactic center.

Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis from a collection of posed input images. Like most view synthesis methods, NeRF uses tonemapped low dynamic range (LDR) as input; these images have been processed by a lossy camera pipeline that smooths detail, clips highlights, and distorts the simple noise distribution of raw sensor data. We modify NeRF to instead train directly on linear raw images, preserving the scene's full dynamic range. By rendering raw output images from the resulting NeRF, we can perform novel high dynamic range (HDR) view synthesis tasks. In addition to changing the camera viewpoint, we can manipulate focus, exposure, and tonemapping after the fact. Although a single raw image appears significantly more noisy than a postprocessed one, we show that NeRF is highly robust to the zeromean distribution of raw noise. When optimized over many noisy raw inputs (25–200), NeRF produces a scene representation so accurate that its rendered novel views outperform dedicated single and multi-image deep raw denoisers run on the same wide baseline input images. As a result, our method, which we call RawNeRF, can reconstruct scenes from extremely noisy images captured in near-darkness.

The goal of this work is to perform 3D reconstruction and novel view synthesis from data captured by scanning platforms commonly deployed for world mapping in urban outdoor environments (e.g., Street View). Given a sequence of posed RGB images and lidar sweeps acquired by cameras and scanners moving through an outdoor scene, we produce a model from which 3D surfaces can be extracted and novel RGB images can be synthesized. Our approach extends Neural Radiance Fields, which has been demonstrated to synthesize realistic novel images for small scenes in controlled settings, with new methods for leveraging asynchronously captured lidar data, for addressing exposure variation between captured images, and for leveraging predicted image segmentations to supervise densities on rays pointing at the sky. Each of these three extensions provides significant performance improvements in experiments on Street View data. Our system produces state-of-the-art 3D surface reconstructions and synthesizes higher quality novel views in comparison to both traditional methods (e.g. COLMAP) and recent neural representations (e.g. Mip-NeRF).

Neural radiance fields (NeRF) encode a scene into a neural representation that enables photo-realistic rendering of novel views. However, a successful reconstruction from RGB images requires a large number of input views taken under static conditions — typically up to a few hundred images for room-size scenes. Our method aims to synthesize novel views of whole rooms from an order of magnitude fewer images. To this end, we leverage dense depth priors in order to constrain the NeRF optimization. First, we take advantage of the sparse depth data that is freely available from the structure from motion (SfM) preprocessing step used to estimate camera poses. Second, we use depth completion to convert these sparse points into dense depth maps and uncertainty estimates, which are used to guide NeRF optimization. Our method enables data-efficient novel view synthesis on challenging indoor scenes, using as few as 18 images for an entire scene.

We present Block-NeRF, a variant of Neural Radiance Fields that can represent large-scale environments. Specifically, we demonstrate that when scaling NeRF to render city-scale scenes spanning multiple blocks, it is vital to de-compose the scene into individually trained NeRFs. This decomposition decouples rendering time from scene size, enables rendering to scale to arbitrarily large environments, and allows per-block updates of the environment. We adopt several architectural changes to make NeRF robust to data captured over months under different environmental conditions. We add appearance embeddings, learned pose refinement, and controllable exposure to each individual NeRF, and introduce a procedure for aligning appearance between adjacent NeRFs so that they can be seamlessly combined. We build a grid of Block-NeRFs from 2.8 million images to create the largest neural scene representation to date, capable of rendering an entire neighborhood of San Francisco.

Neural Radiance Fields (NeRF) is a popular view synthesis technique that represents a scene as a continuous volumetric function, parameterized by multilayer perceptrons that provide the volume density and view-dependent emitted radiance at each location. While NeRF-based techniques excel at representing fine geometric structures with smoothly varying view-dependent appearance, they often fail to accurately capture and reproduce the appearance of glossy surfaces. We address this limitation by introducing Ref-NeRF, which replaces NeRF's parameterization of view-dependent outgoing radiance with a representation of reflected radiance and structures this function using a collection of spatially-varying scene properties. We show that together with a regularizer on normal vectors, our model significantly improves the realism and accuracy of specular reflections. Furthermore, we show that our model's internal representation of outgoing radiance is interpretable and useful for scene editing.

We introduce a free-viewpoint rendering method - HumanNeRF - that works on a given monocular video of a human performing complex body motions, e.g. a video from YouTube. Our method enables pausing the video at any frame and rendering the subject from arbitrary new camera viewpoints or even a full 360-degree camera path for that particular frame and body pose. This task is particularly challenging, as it requires synthesizing photorealistic details of the body, as seen from various camera angles that may not exist in the input video, as well as synthesizing fine details such as cloth folds and facial appearance. Our method optimizes for a volumetric representation of the person in a canonical T-pose, in concert with a motion field that maps the estimated canonical representation to every frame of the video via backward warps. The motion field is decomposed into skeletal rigid and non-rigid motions, produced by deep networks. We show significant performance improvements over prior work, and compelling examples of free-viewpoint renderings from monocular video of moving humans in challenging uncontrolled capture scenarios.

Abstract Synthesizing photo‐realistic images and videos is at the heart of computer graphics and has been the focus of decades of research. Traditionally, synthetic images of a scene are generated using rendering algorithms such as rasterization or ray tracing, which take specifically defined representations of geometry and material properties as input. Collectively, these inputs define the actual scene and what is rendered, and are referred to as the scene representation (where a scene consists of one or more objects). Example scene representations are triangle meshes with accompanied textures (e.g., created by an artist), point clouds (e.g., from a depth sensor), volumetric grids (e.g., from a CT scan), or implicit surface functions (e.g., truncated signed distance fields). The reconstruction of such a scene representation from observations using differentiable rendering losses is known as inverse graphics or inverse rendering. Neural rendering is closely related, and combines ideas from classical computer graphics and machine learning to create algorithms for synthesizing images from real‐world observations. Neural rendering is a leap forward towards the goal of synthesizing photo‐realistic image and video content. In recent years, we have seen immense progress in this field through hundreds of publications that show different ways to inject learnable components into the rendering pipeline. This state‐of‐the‐art report on advances in neural rendering focuses on methods that combine classical rendering principles with learned 3D scene representations, often now referred to as neural scene representations. A key advantage of these methods is that they are 3D‐consistent by design, enabling applications such as novel viewpoint synthesis of a captured scene. In addition to methods that handle static scenes, we cover neural scene representations for modeling non‐rigidly deforming objects and scene editing and composition. While most of these approaches are scene‐specific, we also discuss techniques that generalize across object classes and can be used for generative tasks. In addition to reviewing these state‐of‐the‐art methods, we provide an overview of fundamental concepts and definitions used in the current literature. We conclude with a discussion on open challenges and social implications.

We present a method that takes as input a set of images of a scene illuminated by unconstrained known lighting, and produces as output a 3D representation that can be rendered from novel viewpoints under arbitrary lighting conditions. Our method represents the scene as a continuous volumetric function parameterized as MLPs whose inputs are a 3D location and whose outputs are the following scene properties at that input location: volume density, surface normal, material parameters, distance to the first surface intersection in any direction, and visibility of the external environment in any direction. Together, these allow us to render novel views of the object under arbitrary lighting, including indirect illumination effects. The predicted visibility and surface intersection fields are critical to our model’s ability to simulate direct and indirect illumination during training, because the brute-force techniques used by prior work are intractable for lighting conditions outside of controlled setups with a single light. Our method outperforms alternative approaches for recovering relightable 3D scene representations, and performs well in complex lighting settings that have posed a significant challenge to prior work.

Coordinate-based neural representations have shown significant promise as an alternative to discrete, array-based representations for complex low dimensional signals. However, optimizing a coordinate-based network from randomly initialized weights for each new signal is inefficient. We propose applying standard meta-learning algorithms to learn the initial weight parameters for these fully-connected networks based on the underlying class of signals being represented (e.g., images of faces or 3D models of chairs). Despite requiring only a minor change in implementation, using these learned initial weights enables faster convergence during optimization and can serve as a strong prior over the signal class being modeled, resulting in better generalization when only partial observations of a given signal are available. We explore these benefits across a variety of tasks, including representing 2D images, reconstructing CT scans, and recovering 3D shapes and scenes from 2D image observations.

We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates radiance and volume density at continuous 5D locations (3D spatial locations and 2D viewing directions), drawing appearance information on the fly from multiple source views. By drawing on source views at render time, our method hearkens back to classic work on image-based rendering (IBR), and allows us to render high-resolution imagery. Unlike neural scene representation work that optimizes per-scene functions for rendering, we learn a generic view interpolation function that generalizes to novel scenes. We render images using classic volume rendering, which is fully differentiable and allows us to train using only multi-view posed images as supervision. Experiments show that our method outperforms recent novel view synthesis methods that also seek to generalize to novel scenes. Further, if fine-tuned on each scene, our method is competitive with state-of-the-art single-scene neural rendering methods.1

The rendering procedure used by neural radiance fields (NeRF) samples a scene with a single ray per pixel and may therefore produce renderings that are excessively blurred or aliased when training or testing images observe scene content at different resolutions. The straightforward solution of supersampling by rendering with multiple rays per pixel is impractical for NeRF, because rendering each ray requires querying a multilayer perceptron hundreds of times. Our solution, which we call "mip-NeRF" (à la "mipmap"), extends NeRF to represent the scene at a continuously-valued scale. By efficiently rendering anti-aliased conical frustums instead of rays, mip-NeRF reduces objectionable aliasing artifacts and significantly improves NeRF’s ability to represent fine details, while also being 7% faster than NeRF and half the size. Compared to NeRF, mip-NeRF reduces average error rates by 17% on the dataset presented with NeRF and by 60% on a challenging multiscale variant of that dataset that we present. Mip-NeRF is also able to match the accuracy of a brute-force supersampled NeRF on our multiscale dataset while being 22× faster.

Neural volumetric representations such as Neural Radiance Fields (NeRF) have emerged as a compelling technique for learning to represent 3D scenes from images with the goal of rendering photorealistic images of the scene from unobserved viewpoints. However, NeRF’s computational requirements are prohibitive for real-time applications: rendering views from a trained NeRF requires querying a multilayer perceptron (MLP) hundreds of times per ray. We present a method to train a NeRF, then precompute and store (i.e. "bake") it as a novel representation called a Sparse Neural Radiance Grid (SNeRG) that enables real-time rendering on commodity hardware. To achieve this, we introduce 1) a reformulation of NeRF’s architecture, and 2) a sparse voxel grid representation with learned feature vectors. The resulting scene representation retains NeRF’s ability to render fine geometric details and view-dependent appearance, is compact (averaging less than 90 MB per scene), and can be rendered in real-time (higher than 30 frames per second on a laptop GPU). Actual screen captures are shown in our video.

We present a method that takes as input a single dual-pixel image, and simultaneously estimates the image’s defocus map—the amount of defocus blur at each pixel—and recovers an all-in-focus image. Our method is inspired from recent works that leverage the dual-pixel sensors available in many consumer cameras to assist with autofocus, and use them for recovery of defocus maps or all-in-focus images. These prior works have solved the two recovery problems independently of each other, and often require large labeled datasets for supervised training. By contrast, we show that it is beneficial to treat these two closely-connected problems simultaneously. To this end, we set up an optimization problem that, by carefully modeling the optics of dual-pixel images, jointly solves both problems. We use data captured with a consumer smartphone camera to demonstrate that, after a one-time calibration step, our approach improves upon prior works for both defocus map estimation and blur removal, despite being entirely unsupervised.

We address the problem of recovering the shape and spatially-varying reflectance of an object from multi-view images (and their camera poses) of an object illuminated by one unknown lighting condition. This enables the rendering of novel views of the object under arbitrary environment lighting and editing of the object's material properties. The key to our approach, which we call Neural Radiance Factorization (NeRFactor), is to distill the volumetric geometry of a Neural Radiance Field (NeRF) [Mildenhall et al. 2020] representation of the object into a surface representation and then jointly refine the geometry while solving for the spatially-varying reflectance and environment lighting. Specifically, NeRFactor recovers 3D neural fields of surface normals, light visibility, albedo, and Bidirectional Reflectance Distribution Functions (BRDFs) without any supervision, using only a re-rendering loss, simple smoothness priors, and a data-driven BRDF prior learned from real-world BRDF measurements. By explicitly modeling light visibility, NeRFactor is able to separate shadows from albedo and synthesize realistic soft or hard shadows under arbitrary lighting conditions. NeRFactor is able to recover convincing 3D models for free-viewpoint relighting in this challenging and underconstrained capture setup for both synthetic and real scenes. Qualitative and quantitative experiments show that NeRFactor outperforms classic and deep learning-based state of the art across various tasks. Our videos, code, and data are available at people.csail.mit.edu/xiuming/projects/nerfactor/.

We present a deep learning solution for estimating the incident illumination at any 3D location within a scene from an input narrow-baseline stereo image pair. Previous approaches for predicting global illumination from images either predict just a single illumination for the entire scene, or separately estimate the illumination at each 3D location without enforcing that the predictions are consistent with the same 3D scene. Instead, we propose a deep learning model that estimates a 3D volumetric RGBA model of a scene, including content outside the observed field of view, and then uses standard volume rendering to estimate the incident illumination at any 3D location within that volume. Our model is trained without any ground truth 3D data and only requires a held-out perspective view near the input stereo pair and a spherical panorama taken within each scene as supervision, as opposed to prior methods for spatially-varying lighting estimation, which require ground truth scene geometry for training. We demonstrate that our method can predict consistent spatially-varying lighting that is convincing enough to plausibly relight and insert highly specular virtual objects into real images.

We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domains. These results shed light on recent advances in computer vision and graphics that achieve state-of-the-art results by using MLPs to represent complex 3D objects and scenes. Using tools from the neural tangent kernel (NTK) literature, we show that a standard MLP has impractically slow convergence to high frequency signal components. To overcome this spectral bias, we use a Fourier feature mapping to transform the effective NTK into a stationary kernel with a tunable bandwidth. We suggest an approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities.

We explore the problem of view synthesis from a narrow baseline pair of images, and focus on generating high-quality view extrapolations with plausible disocclusions. Our method builds upon prior work in predicting a multiplane image (MPI), which represents scene content as a set of RGBA planes within a reference view frustum and renders novel views by projecting this content into the target viewpoints. We present a theoretical analysis showing how the range of views that can be rendered from an MPI increases linearly with the MPI disparity sampling frequency, as well as a novel MPI prediction procedure that theoretically enables view extrapolations of up to 4 times the lateral viewpoint movement allowed by prior work. Our method ameliorates two specific issues that limit the range of views renderable by prior methods: 1) We expand the range of novel views that can be rendered without depth discretization artifacts by using a 3D convolutional network architecture along with a randomized-resolution training procedure to allow our model to predict MPIs with increased disparity sampling frequency. 2) We reduce the repeated texture artifacts seen in disocclusions by enforcing a constraint that the appearance of hidden content at any depth must be drawn from visible content at or behind that depth.

We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration. Previous approaches either require intractably dense view sampling or provide little to no guidance for how users should sample views of a scene to reliably render high-quality novel views. Instead, we propose an algorithm for view synthesis from an irregular grid of sampled views that first expands each sampled view into a local light field via a multiplane image (MPI) scene representation, then renders novel views by blending adjacent local light fields. We extend traditional plenoptic sampling theory to derive a bound that specifies precisely how densely users should sample views of a given scene when using our algorithm. In practice, we apply this bound to capture and render views of real world scenes that achieve the perceptual quality of Nyquist rate view sampling while using up to 4000X fewer views. We demonstrate our approach's practicality with an augmented reality smart-phone app that guides users to capture input images of a scene and viewers that enable realtime virtual exploration on desktop and mobile platforms.

We present a novel method to train machine learning algorithms to estimate scene depths from a single image, by using the information provided by a camera's aperture as supervision. Prior works use a depth sensor's outputs or images of the same scene from alternate viewpoints as supervision, while our method instead uses images from the same viewpoint taken with a varying camera aperture. To enable learning algorithms to use aperture effects as supervision, we introduce two differentiable aperture rendering functions that use the input image and predicted depths to simulate the depth-of-field effects caused by real camera apertures. We train a monocular depth estimation network end-to-end to predict the scene depths that best explain these finite aperture images as defocus-blurred renderings of the input all-in-focus image.

We study the problem of deblurring light fields of general 3D scenes captured under 3D camera motion and present both theoretical and practical contributions. By analyzing the motion-blurred light field in the primal and Fourier domains, we develop intuition into the effects of camera motion on the light field, show the advantages of capturing a 4D light field instead of a conventional 2D image for motion deblurring, and derive simple analytical methods of motion deblurring in certain cases. We then present an algorithm to blindly deblur light fields of general scenes without any estimation of scene geometry, and demonstrate that we can recover both the sharp light field and the 3D camera motion path of real and synthetically-blurred light fields.

We present a machine learning algorithm that takes as input a 2D RGB image and synthesizes a 4D RGBD light field (color and depth of the scene in each ray direction). For training, we introduce the largest public light field dataset, consisting of over 3300 plenoptic camera light fields of scenes containing flowers and plants. Our synthesis pipeline consists of a convolutional neural network (CNN) that estimates scene geometry, a stage that renders a Lambertian light field using that geometry, and a second CNN that predicts occluded rays and non-Lambertian effects. Our algorithm builds on recent view synthesis methods, but is unique in predicting RGBD for each light field ray and improving unsupervised single image depth estimation by enforcing consistency of ray depths that should intersect the same scene point.

Light-field cameras are quickly becoming commodity items, with consumer and industrial applications. They capture many nearby views simultaneously using a single image with a micro-lens array, thereby providing a wealth of cues for depth recovery: defocus, correspondence, and shading. In particular, apart from conventional image shading, one can refocus images after acquisition, and shift one's viewpoint within the sub-apertures of the main lens, effectively obtaining multiple views. We present a principled algorithm for dense depth estimation that combines defocus and correspondence metrics. We then extend our analysis to the additional cue of shading, using it to refine fine details in the shape. By exploiting an all-in-focus image, in which pixels are expected to exhibit angular coherence, we define an optimization framework that integrates photo consistency, depth consistency, and shading consistency. We show that combining all three sources of information: defocus, correspondence, and shading, outperforms state-of-the-art light-field depth estimation algorithms in multiple scenarios.

Computer-graphics engineers and vision scientists want to generate images that reproduce realistic depth-dependent blur. Current rendering algorithms take into account scene geometry, aperture size, and focal distance, and they produce photorealistic imagery as with a high-quality camera. But to create immersive experiences, rendering algorithms should aim instead for perceptual realism. In so doing, they should take into account the significant optical aberrations of the human eye. We developed a method that, by incorporating some of those aberrations, yields displayed images that produce retinal images much closer to the ones that occur in natural viewing. In particular, we create displayed images taking the eye's chromatic aberration into account. This produces different chromatic effects in the retinal image for objects farther or nearer than current focus. We call the method ChromaBlur. We conducted two experiments that illustrate the benefits of ChromaBlur. One showed that accommodation (eye focusing) is driven quite effectively when ChromaBlur is used and that accommodation is not driven at all when conventional methods are used. The second showed that perceived depth and realism are greater with imagery created by ChromaBlur than in imagery created conventionally. ChromaBlur can be coupled with focus-adjustable lenses and gaze tracking to reproduce the natural relationship between accommodation and blur in HMDs and other immersive devices. It may thereby minimize the adverse effects of vergence-accommodation conflicts.

Light-field cameras are now used in consumer and industrial applications. Recent papers and products have demonstrated practical depth recovery algorithms from a passive single-shot capture. However, current light-field capture devices have narrow baselines and constrained spatial resolution; therefore, the accuracy of depth recovery is limited, requiring heavy regularization and producing planar depths that do not resemble the actual geometry. Using shading information is essential to improve the shape estimation. We develop an improved technique for local shape estimation from defocus and correspondence cues, and show how shading can be used to further refine the depth. Light-field cameras are able to capture both spatial and angular data, suitable for refocusing. By locally refocusing each spatial pixel to its respective estimated depth, we produce an all-in-focus image where all viewpoints converge onto a point in the scene. Therefore, the angular pixels have angular coherence, which exhibits three properties: photo consistency, depth consistency, and shading consistency. We propose a new framework that uses angular coherence to optimize depth and shading. The optimization framework estimates both general lighting in natural scenes and shading to improve depth regularization. Our method outperforms current state-of-the-art light-field depth estimation algorithms in multiple scenarios, including real images.

2D spatial image windows are used for comparing pixel values in computer vision applications such as correspondence for optical flow and 3D reconstruction, bilateral filtering, and image segmentation. However, pixel window comparisons can suffer from varying defocus blur and perspective at different depths, and can also lead to a loss of precision. In this paper, we leverage the recent use of light-field cameras to propose alternative oriented light-field windows that enable more robust and accurate pixel comparisons. For Lambertian surfaces focused to the correct depth, the 2D distribution of angular rays from a pixel remains consistent. We build on this idea to develop an oriented 4D light-field window that accounts for shearing (depth), translation (matching), and windowing. Our main application is to scene flow, a generalization of optical flow to the 3D vector field describing the motion of each point in the scene. We show significant benefits of oriented light-field windows over standard 2D spatial windows. We also demonstrate additional applications of oriented light-field windows for bilateral filtering and image segmentation.