Large-scale AI model training divides work across thousands of GPUs, then synchronizes gradients across them at each step. This incurs a significant network burden that only centralized, monolithic clusters can support, driving up infrastructure costs and straining power systems. We propose Decentralized Diffusion Models, a scalable framework for distributing diffusion model training across independent clusters or datacenters by eliminating the dependence on a centralized, high-bandwidth networking fabric. Our method trains a set of expert diffusion models over partitions of the dataset, each in full isolation from one another. At inference time, the experts ensemble through a lightweight router. We show that the ensemble collectively optimizes the same objective as a single model trained over the whole dataset. This means we can divide the training burden among a number of “compute islands,” lowering infrastructure costs and improving resilience to localized GPU failures. Decentralized diffusion models empower researchers to take advantage of smaller, more cost-effective and more readily available compute like on-demand GPU nodes rather than central integrated systems. We conduct extensive experiments on ImageNet and LAION Aesthetics, showing that decentralized diffusion models FLOP-for-FLOP outperform standard diffusion models. We finally scale our approach to 24 billion parameters, demonstrating that high-quality diffusion models can now be trained with just eight individual GPU nodes in less than a week.

gsplat is an open-source library designed for training and developing Gaussian Splatting methods. It features a front-end with Python bindings compatible with the PyTorch library and a back-end with highly optimized CUDA kernels. gsplat offers numerous features that enhance the optimization of Gaussian Splatting models, which include optimization improvements for speed, memory, and convergence times. Experimental results demonstrate that gsplat achieves up to 10% less training time and 4x less memory than the original implementation. Utilized in several research projects, gsplat is actively maintained on GitHub. Source code is available at https://github.com/nerfstudio-project/gsplat under Apache License 2.0. We welcome contributions from the open-source community.

Grouping is inherently ambiguous due to the multiple levels of granularity in which one can decompose a sceneshould the wheels of an excavator be considered separate or part of the whole? We propose Group Anything with Radiance Fields (GARField), an approach for decomposing 3D scenes into a hierarchy of semantically meaningful groups from posed image inputs. To do this we embrace group ambiguity through physical scale: by optimizing a scaleconditioned 3D affinity feature field, a point in the world can belong to different groups of different sizes. We optimize this field from a set of 2D masks provided by Segment Anything (SAM) in a way that respects coarse-to-fine hierarchy, using scale to consistently fuse conflicting masks from different viewpoints. From this field we can derive a hierarchy of possible groupings via automatic tree construction or user interaction. We evaluate GARField on a variety of in-the-wild scenes and find it effectively extracts groups at many levels: clusters of objects, objects, and various subparts. GARField inherently represents multi-view consistent groupings and produces higher fidelity groups than the input SAM masks. GARField's hierarchical grouping could have exciting downstream applications such as 3D asset extraction or dynamic scene understanding. Project site: https://www.garfield.studio/

We propose a method for editing NeRF scenes with text-instructions. Given a NeRF of a scene and the collection of images used to reconstruct it, our method uses an image-conditioned diffusion model (InstructPix2Pix) to iteratively edit the input images while optimizing the underlying scene, resulting in an optimized 3D scene that respects the edit instruction. We demonstrate that our proposed method is able to edit large-scale, real-world scenes, and is able to accomplish more realistic, targeted edits than prior work. Result videos can be found on the project website: https://instruct-nerf2nerf.github.io.

Humans describe the physical world using natural language to refer to specific 3D locations based on a vast range of properties: visual appearance, semantics, abstract associations, or actionable affordances. In this work we propose Language Embedded Radiance Fields (LERFs), a method for grounding language embeddings from off-the-shelf models like CLIP into NeRF, which enable these types of open-ended language queries in 3D. LERF learns a dense, multi-scale language field inside NeRF by volume rendering CLIP embeddings along training rays, supervising these embeddings across training views to provide multi-view consistency and smooth the underlying language field. After optimization, LERF can extract 3D relevancy maps for a broad range of language prompts interactively in real-time, which has potential use cases in robotics, understanding vision-language models, and interacting with 3D scenes. LERF enables pixel-aligned, zero-shot queries on the distilled 3D CLIP embeddings without relying on region proposals or masks, supporting long-tail open-vocabulary queries hierarchically across the volume. See the project website at: https://lerf.io.

Optimizing and rendering Neural Radiance Fields is computationally expensive due to the vast number of samples required by volume rendering. Recent works have included alternative sampling approaches to help accelerate their methods, however, they are often not the focus of the work. In this paper, we investigate and compare multiple sampling approaches and demonstrate that improved sampling is generally applicable across NeRF variants under an unified concept of transmittance estimator. To facilitate future experiments, we develop NerfAcc, a Python toolbox that provides flexible APIs for incorporating advanced sampling methods into NeRF related methods. We demonstrate its flexibility by showing that it can reduce the training time of several recent NeRF methods by 1.5× to 20× with minimal modifications to the existing codebase. Additionally, highly customized NeRFs, such as Instant-NGP, can be implemented in native PyTorch using NerfAcc. Our code are open-sourced at https://www.nerfacc.com.

Casually captured Neural Radiance Fields (NeRFs) suffer from artifacts such as floaters or flawed geometry when rendered outside the input camera trajectory. Existing evaluation protocols often do not capture these effects, since they usually only assess image quality at every 8th frame of the training capture. To aid in the development and evaluation of new methods in novel-view synthesis, we propose a new dataset and evaluation procedure, where two camera trajectories are recorded of the scene: one used for training, and the other for evaluation. In this more challenging in-the-wild setting, we find that existing hand-crafted regularizers do not remove floaters nor improve scene geometry. Thus, we propose a 3D diffusion-based method that leverages local 3D priors and a novel density-based score distillation sampling loss to discourage artifacts during NeRF optimization. We show that this data-driven prior removes floaters and improves scene geometry for casual captures.

We introduce Plenoxels (plenoptic voxels), a systemfor photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation can be optimized from calibrated images via gradient methods and regularization without any neural components. On standard, benchmark tasks, Plenoxels are optimized two orders of magnitude faster than Neural Radiance Fields with no loss in visual quality. For video and code, please see https://alexyu.net/plenoxels.

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.

Widely used in news, business, and educational media, infographics are handcrafted to effectively communicate messages about complex and often abstract topics including `ways to conserve the environment' and `coronavirus prevention'. The computational understanding of infographics required for future applications like automatic captioning, summarization, search, and question-answering, will depend on being able to parse the visual and textual elements contained within. However, being composed of stylistically and semantically diverse visual and textual elements, infographics pose challenges for current A.I. systems. While automatic text extraction works reasonably well on infographics, standard object detection algorithms fail to identify the stand-alone visual elements in infographics that we refer to as `icons'. In this paper, we propose a novel approach to train an object detector using synthetically-generated data, and show that it succeeds at generalizing to detecting icons within in-the-wild infographics. We further pair our icon detection approach with an icon classifier and a state-of-the-art text detector to demonstrate three demo applications: topic prediction, multi-modal summarization, and multi-modal search. Parsing the visual and textual elements within infographics provides us with the first steps towards automatic infographic understanding.

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 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.

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.

We present DietNeRF, a 3D neural scene representation estimated from a few images. Neural Radiance Fields (NeRF) learn a continuous volumetric representation of a scene through multi-view consistency, and can be rendered from novel viewpoints by ray casting. While NeRF has an impressive ability to reconstruct geometry and fine details given many images, up to 100 for challenging 360° scenes, it often finds a degenerate solution to its image reconstruction objective when only a few input views are available. To improve few-shot quality, we propose DietNeRF. We introduce an auxiliary semantic consistency loss that encourages realistic renderings at novel poses. DietNeRF is trained on individual scenes to (1) correctly render given input views from the same pose, and (2) match high-level semantic attributes across different, random poses. Our semantic loss allows us to supervise DietNeRF from arbitrary poses. We extract these semantics using a pre-trained visual encoder such as CLIP, a Vision Transformer trained on hundreds of millions of diverse single-view, 2D photographs mined from the web with natural language supervision. In experiments, DietNeRF improves the perceptual quality of few-shot view synthesis when learned from scratch, can render novel views with as few as one observed image when pre-trained on a multi-view dataset, and produces plausible completions of completely unobserved regions. Our project website is available at https://www.ajayj.com/dietnerf.

We introduce a method to render Neural Radiance Fields (NeRFs) in real time using PlenOctrees, an octree-based 3D representation which supports view-dependent effects. Our method can render 800×800 images at more than 150 FPS, which is over 3000 times faster than conventional NeRFs. We do so without sacrificing quality while preserving the ability of NeRFs to perform free-viewpoint rendering of scenes with arbitrary geometry and view-dependent effects. Real-time performance is achieved by pre-tabulating the NeRF into a PlenOctree. In order to preserve view-dependent effects such as specularities, we factorize the appearance via closed-form spherical basis functions. Specifically, we show that it is possible to train NeRFs to predict a spherical harmonic representation of radiance, removing the viewing direction as an input to the neural network. Furthermore, we show that PlenOctrees can be directly optimized to further minimize the reconstruction loss, which leads to equal or better quality compared to competing methods. Moreover, this octree optimization step can be used to reduce the training time, as we no longer need to wait for the NeRF training to converge fully. Our real-time neural rendering approach may potentially enable new applications such as 6-DOF industrial and product visualizations, as well as next generation AR/VR systems. PlenOctrees are amenable to in-browser rendering as well; please visit the project page for the interactive online demo, as well as video and code: https://alexyu.net/plenoctrees.

Eye movements provide insight into what parts of an image a viewer finds most salient, interesting, or relevant to the task at hand. Unfortunately, eye tracking data, a commonly-used proxy for attention, is cumbersome to collect. Here we explore an alternative: a comprehensive web-based toolbox for crowdsourcing visual attention. We draw from four main classes of attention-capturing methodologies in the literature. ZoomMaps is a novel zoom-based interface that captures viewing on a mobile phone. CodeCharts is a self-reporting methodology that records points of interest at precise viewing durations. ImportAnnots is an "annotation" tool for selecting important image regions, and cursor-based BubbleView lets viewers click to deblur a small area. We compare these methodologies using a common analysis framework in order to develop appropriate use cases for each interface. This toolbox and our analyses provide a blueprint for how to gather attention data at scale without an eye tracker.

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.

Printed and digitally displayed photos have the ability to hide imperceptible digital data that can be accessed through internet-connected imaging systems. Another way to think about this is physical photographs that have unique QR codes invisibly embedded within them. This paper presents an architecture, algorithms, and a prototype implementation addressing this vision. Our key technical contribution is StegaStamp, a learned steganographic algorithm to enable robust encoding and decoding of arbitrary hyperlink bitstrings into photos in a manner that approaches perceptual invisibility. StegaStamp comprises a deep neural network that learns an encoding/decoding algorithm robust to image perturbations approximating the space of distortions resulting from real printing and photography. We demonstrates real-time decoding of hyperlinks in photos from in-the-wild videos that contain variation in lighting, shadows, perspective, occlusion and viewing distance. Our prototype system robustly retrieves 56 bit hyperlinks after error correction -- sufficient to embed a unique code within every photo on the internet.

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.

Imaging through fog has important applications in industries such as self-driving cars, augmented driving, airplanes, helicopters, drones and trains. Here we show that time profiles of light reflected from fog have a distribution (Gamma) that is different from light reflected from objects occluded by fog (Gaussian). This helps to distinguish between background photons reflected from the fog and signal photons reflected from the occluded object. Based on this observation, we recover reflectance and depth of a scene obstructed by dense, dynamic, and heterogeneous fog. For practical use cases, the imaging system is designed in optical reflection mode with minimal footprint and is based on LIDAR hardware. Specifically, we use a single photon avalanche diode (SPAD) camera that time-tags individual detected photons. A probabilistic computational framework is developed to estimate the fog properties from the measurement itself, without prior knowledge. Other solutions are based on radar that suffers from poor resolution (due to the long wavelength), or on time gating that suffers from low signal-to-noise ratio. The suggested technique is experimentally evaluated in a wide range of fog densities created in a fog chamber It demonstrates recovering objects 57cm away from the camera when the visibility is 37cm. In that case it recovers depth with a resolution of 5cm and scene reflectance with an improvement of 4dB in PSNR and 3.4× reconstruction quality in SSIM over time gating techniques.