skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Friday, April 12 until 2:00 AM ET on Saturday, April 13 due to maintenance. We apologize for the inconvenience.

This content will become publicly available on December 5, 2024

Title: ScaNeRF: Scalable Bundle-Adjusting Neural Radiance Fields for Large-Scale Scene Rendering

High-quality large-scale scene rendering requires a scalable representation and accurate camera poses. This research combines tile-based hybrid neural fields with parallel distributive optimization to improve bundle-adjusting neural radiance fields. The proposed method scales with a divide-and-conquer strategy. We partition scenes into tiles, each with a multi-resolution hash feature grid and shallow chained diffuse and specular multilayer perceptrons (MLPs). Tiles unify foreground and background via a spatial contraction function that allows both distant objects in outdoor scenes and planar reflections as virtual images outside the tile. Decomposing appearance with the specular MLP allows a specular-aware warping loss to provide a second optimization path for camera poses. We apply the alternating direction method of multipliers (ADMM) to achieve consensus among camera poses while maintaining parallel tile optimization. Experimental results show that our method outperforms state-of-the-art neural scene rendering method quality by 5%--10% in PSNR, maintaining sharp distant objects and view-dependent reflections across six indoor and outdoor scenes.

more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ; ; ;
Publisher / Repository:
Date Published:
Journal Name:
ACM Transactions on Graphics
Page Range / eLocation ID:
1 to 18
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. We use neural radiance fields (NeRFs) to build interactive 3D environments from large-scale visual captures spanning buildings or even multiple city blocks collected primarily from drones. In contrast to single object scenes (on which NeRFs are traditionally evaluated), our scale poses multiple challenges including (1) the need to model thousands of images with varying lighting conditions, each of which capture only a small subset of the scene, (2) prohibitively large model capacities that make it infeasible to train on a single GPU, and (3) significant challenges for fast rendering that would enable interactive fly-throughs. To address these challenges, we begin by analyzing visibility statistics for large-scale scenes, motivating a sparse network structure where parameters are specialized to different regions of the scene. We introduce a simple geometric clustering algorithm for data parallelism that partitions training images (or rather pixels) into different NeRF sub-modules that can be trained in parallel. We evaluate our approach on existing datasets (Quad 6k and UrbanScene3D) as well as against our own drone footage, improving training speed by 3x and PSNR by 12%. We also evaluate recent NeRF fast renderers on top of Mega-NeRF and introduce a novel method that exploits temporal coherence. Our technique achieves a 40x speedup over conventional NeRF rendering while remaining within 0.8 db in PSNR quality, exceeding the fidelity of existing fast renderers. 
    more » « less
  2. This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S2fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established key-point correspondences. Our novel formulation poses some new challenges due to inevitable two-view and few-view configurations in the incremental SfM pipeline, which complicates the optimization of coordinate MLPs for volumetric neural rendering with unknown camera poses. Nevertheless, we demonstrate that the strong inductive basis conveying in the 2D correspondences is promising to tackle those challenges by exploiting the relationship between the ray sampling schemes. Based on this, we revisit the pipeline of incremental SfM and renew the key components, including two-view geometry initialization, the camera poses registration, the 3D points triangulation, and Bundle Adjustment, with a fresh perspective based on neural implicit surfaces. By unifying the scene geometry in small MLP networks through coordinate MLPs, our Level-S2fM treats the zero-level set of the implicit surface as an informative top-down regularization to manage the reconstructed 3D points, reject the outliers in correspondences via querying SDF, and refine the estimated geometries by NBA (Neural BA). Not only does our Level-S2fM lead to promising results on camera pose estimation and scene geometry reconstruction, but it also shows a promising way for neural implicit rendering without knowing camera extrinsic beforehand. 
    more » « less
  3. This paper focuses on vision-based pose estimation for multiple rigid objects placed in clutter, especially in cases involving occlusions and objects resting on each other. Progress has been achieved recently in object recognition given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their applicability in robotics, where solutions must scale to a large number of objects and variety of conditions. Moreover, the combinatorial nature of the scenes that could arise from the placement of multiple objects is hard to capture in the training dataset. Thus, the learned models might not produce the desired level of precision required for tasks, such as robotic manipulation. This work proposes an autonomous process for pose estimation that spans from data generation to scene-level reasoning and self-learning. In particular, the proposed framework first generates a labeled dataset for training a Convolutional Neural Network (CNN) for object detection in clutter. These detections are used to guide a scene-level optimization process, which considers the interactions between the different objects present in the clutter to output pose estimates of high precision. Furthermore, confident estimates are used to label online real images from multiple views and re-train the process in a self-learning pipeline. Experimental results indicate that this process is quickly able to identify in cluttered scenes physically-consistent object poses that are more precise than the ones found by reasoning over individual instances of objects. Furthermore, the quality of pose estimates increases over time given the self-learning process. 
    more » « less
  4. Placing and orienting a camera to compose aesthetically meaningful shots of a scene is not only a key objective in real-world photography and cinematography but also for virtual content creation. The framing of a camera often significantly contributes to the story telling in movies, games, and mixed reality applications. Generating single camera poses or even contiguous trajectories either requires a significant amount of manual labor or requires solving highdimensional optimization problems, which can be computationally demanding and error-prone. In this paper, we introduce GAIT, a Deep Reinforcement Learning (DRL) agent, that learns to automatically control a camera to generate a sequence of aesthetically meaningful views for synthetic 3D indoor scenes. To generate sequences of frames with high aesthetic value, GAIT relies on a neural aesthetics estimator, which is trained on a crowed-sourced dataset. Additionally, we introduce regularization techniques for diversity and smoothness to generate visually interesting trajectories for a 3D environment, and to constrain agent acceleration in the reward function to generate a smooth sequence of camera frames. We validated our method by comparing it to baseline algorithms, based on a perceptual user study, and through ablation studies. The source code of our method will be released with the final version of our paper. 
    more » « less
  5. Reconstructing 3D objects in natural environments requires solving the ill-posed problem of geometry, spatially-varying material, and lighting estimation. As such, many approaches impractically constrain to a dark environment, use controlled lighting rigs, or use few handheld captures but suffer reduced quality. We develop a method that uses just two smartphone exposures captured in ambient lighting to reconstruct appearance more accurately and practically than baseline methods. Our insight is that we can use a flash/no-flash RGB-D pair to pose an inverse rendering problem using point lighting. This allows efficient differentiable rendering to optimize depth and normals from a good initialization and so also the simultaneous optimization of diffuse environment illumination and SVBRDF material. We find that this reduces diffuse albedo error by 25%, specular error by 46%, and normal error by 30% against single and paired-image baselines that use learning-based techniques. Given that our approach is practical for everyday solid objects, we enable photorealistic relighting for mobile photography and easier content creation for augmented reality. 
    more » « less