Learn Your Scales: Towards Scale-Consistent Generative Novel View Synthesis

Conventional depth-free multi-view datasets are captured using a moving monocular camera without metric calibration. The scales of camera positions in this monocular setting are ambiguous. Previous methods have acknowledged scale ambiguity in multi-view data via various ad-hoc normalization pre-processing steps, but have not directly analyzed the effect of incorrect scene scales on their application. In this paper, we seek to understand and address the effect of scale ambiguity when used to train generative novel view synthesis methods (GNVS). In GNVS, new views of a scene or object can be minimally synthesized given a single image and are, thus, unconstrained, necessitating the use of generative methods. The generative nature of these models captures all aspects of uncertainty, including any uncertainty of scene scales, which act as nuisance variables for the task. We study the effect of scene scale ambiguity in GNVS when sampled from a single image by isolating its effect on the resulting models and, based on these intuitions, define new metrics that measure the scale inconsistency of generated views. We then propose a framework to estimate scene scales jointly with the GNVS model in an end-to-end fashion. Empirically, we show that our method reduces the scale inconsistency of generated views without the complexity or downsides of previous scale normalization methods. Further, we show that removing this ambiguity improves generated image quality of the resulting GNVS model.

Geometry-Aware Diffusion Models for Multiview Scene Inpainting

In this paper, we focus on 3D scene inpainting, where parts of an input image set, captured from different viewpoints, are masked out. The main challenge lies in generating plausible image completions that are geometrically consistent across views. Most recent work addresses this challenge by combining generative models with a 3D radiance field to fuse information across viewpoints. However, a major drawback of these methods is that they often produce blurry images due to the fusion of inconsistent cross-view images. To avoid blurry inpaintings, we eschew the use of an explicit or implicit radiance field altogether and instead fuse cross-view information in a learned space. In particular, we introduce a geometry-aware conditional generative model, capable of inpainting multi-view consistent images based on both geometric and appearance cues from reference images. A key advantage of our approach over existing methods is its unique ability to inpaint masked scenes with a limited number of views (i.e., few-view inpainting), whereas previous methods require relatively large image sets for their 3D model fitting step. Empirically, we evaluate and compare our scene-centric inpainting method on two datasets, SPIn-NeRF and NeRFiller, which contain images captured at narrow and wide baselines, respectively, and achieve state-of-the-art 3D inpainting performance on both. Additionally, we demonstrate the efficacy of our approach in the few-view setting compared to prior methods.

Efficient Neural Network Encoding for 3D Color Lookup Tables

3D color lookup tables (LUTs) enable precise color manipulation by mapping input RGB values to specific output RGB values. 3D LUTs are instrumental in various applications, including video editing, in-camera processing, photographic filters, computer graphics, and color processing for displays. While an individual LUT does not incur a high memory overhead, software and devices may need to store dozens to hundreds of LUTs that can take over 100 MB. This work aims to develop a neural network architecture that can encode hundreds of LUTs in a single compact representation. To this end, we propose a model with a memory footprint of less than 0.25 MB that can reconstruct 512 LUTs with only minor color distortion ($\bar{\Delta}E_M$ $\leq$ 2.0) over the entire color gamut. We also show that our network can weight colors to provide further quality gains on natural image colors ($\bar{\Delta}{E}_M$ $\leq$ 1.0). Finally, we show that minor modifications to the network architecture enable a bijective encoding that produces LUTs that are invertible, allowing for reverse color processing. Our code is available at https://github.com/vahidzee/ennelut.

Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference

Cryo-Electron Microscopy (cryo-EM) is an increasingly popular experimental technique for estimating the 3D structure of macromolecular complexes such as proteins based on 2D images. These images are notoriously noisy, and the pose of the structure in each image is unknown \textit{a priori}. Ab-initio 3D reconstruction from 2D images entails estimating the pose in addition to the structure. In this work, we propose a new approach to this problem. We first adopt a multi-head architecture as a pose encoder to infer multiple plausible poses per-image in an amortized fashion. This approach mitigates the high uncertainty in pose estimation by encouraging exploration of pose space early in reconstruction. Once uncertainty is reduced, we refine poses in an auto-decoding fashion. In particular, we initialize with the most likely pose and iteratively update it for individual images using stochastic gradient descent (SGD). Through evaluation on synthetic datasets, we demonstrate that our method is able to handle multi-modal pose distributions during the amortized inference stage, while the later, more flexible stage of direct pose optimization yields faster and more accurate convergence of poses compared to baselines. Finally, on experimental data, we show that our approach is faster than state-of-the-art cryoAI and achieves higher-resolution reconstruction.

PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis

This paper considers the problem of generative novel view synthesis (GNVS), generating novel, plausible views of a scene given a limited number of known views. Here, we propose a set-based generative model that can simultaneously generate multiple, self-consistent new views, conditioned on any number of known views. Our approach is not limited to generating a single image at a time and can condition on zero, one, or more views. As a result, when generating a large number of views, our method is not restricted to a low-order autoregressive generation approach and is better able to maintain generated image quality over large sets of images. We evaluate the proposed model on standard NVS datasets and show that it outperforms the state-of-the-art image-based GNVS baselines. Further, we show that the model is capable of generating sets of camera views that have no natural sequential ordering, like loops and binocular trajectories, and significantly outperforms other methods on such tasks.

Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations

Neural Radiance Fields (NeRFs) have proven to be powerful 3D representations, capable of high quality novel view synthesis of complex scenes. While NeRFs have been applied to graphics, vision, and robotics, problems with slow rendering speed and characteristic visual artifacts prevent adoption in many use cases. In this work, we investigate combining an autoencoder (AE) with a NeRF, in which latent features (instead of colours) are rendered and then convolutionally decoded. The resulting latent-space NeRF can produce novel views with higher quality than standard colour-space NeRFs, as the AE can correct certain visual artifacts, while rendering over three times faster. Our work is orthogonal to other techniques for improving NeRF efficiency. Further, we can control the tradeoff between efficiency and image quality by shrinking the AE architecture, achieving over 13 times faster rendering with only a small drop in performance. We hope that our approach can form the basis of an efficient, yet high-fidelity, 3D scene representation for downstream tasks, especially when retaining differentiability is useful, as in many robotics scenarios requiring continual learning.

Dual-Camera Joint Deblurring-Denoising

Recent image enhancement methods have shown the advantages of using a pair of long and short-exposure images for low-light photography. These image modalities offer complementary strengths and weaknesses. The former yields an image that is clean but blurry due to camera or object motion, whereas the latter is sharp but noisy due to low photon count. Motivated by the fact that modern smartphones come equipped with multiple rear-facing camera sensors, we propose a novel dual-camera method for obtaining a high-quality image. Our method uses a synchronized burst of short exposure images captured by one camera and a long exposure image simultaneously captured by another. Having a synchronized short exposure burst alongside the long exposure image enables us to (i) obtain better denoising by using a burst instead of a single image, (ii) recover motion from the burst and use it for motion-aware deblurring of the long exposure image, and (iii) fuse the two results to further enhance quality. Our method is able to achieve state-of-the-art results on synthetic dual-camera images from the GoPro dataset with five times fewer training parameters compared to the next best method. We also show that our method qualitatively outperforms competing approaches on real synchronized dual-camera captures.

Watch Your Steps: Local Image and Scene Editing by Text Instructions

Denoising diffusion models have enabled high-quality image generation and editing. We present a method to localize the desired edit region implicit in a text instruction. We leverage InstructPix2Pix (IP2P) and identify the discrepancy between IP2P predictions with and without the instruction. This discrepancy is referred to as the relevance map. The relevance map conveys the importance of changing each pixel to achieve the edits, and is used to to guide the modifications. This guidance ensures that the irrelevant pixels remain unchanged. Relevance maps are further used to enhance the quality of text-guided editing of 3D scenes in the form of neural radiance fields. A field is trained on relevance maps of training views, denoted as the relevance field, defining the 3D region within which modifications should be made. We perform iterative updates on the training views guided by rendered relevance maps from the relevance field. Our method achieves state-of-the-art performance on both image and NeRF editing tasks. Project page: https://ashmrz.github.io/WatchYourSteps/

Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models

Novel view synthesis from a single input image is a challenging task, where the goal is to generate a new view of a scene from a desired camera pose that may be separated by a large motion. The highly uncertain nature of this synthesis task due to unobserved elements within the scene (i.e., occlusion) and outside the field-of-view makes the use of generative models appealing to capture the variety of possible outputs. In this paper, we propose a novel generative model which is capable of producing a sequence of photorealistic images consistent with a specified camera trajectory, and a single starting image. Our approach is centred on an autoregressive conditional diffusion-based model capable of interpolating visible scene elements, and extrapolating unobserved regions in a view, in a geometrically consistent manner. Conditioning is limited to an image capturing a single camera view and the (relative) pose of the new camera view. To measure the consistency over a sequence of generated views, we introduce a new metric, the thresholded symmetric epipolar distance (TSED), to measure the number of consistent frame pairs in a sequence. While previous methods have been shown to produce high quality images and consistent semantics across pairs of views, we show empirically with our metric that they are often inconsistent with the desired camera poses. In contrast, we demonstrate that our method produces both photorealistic and view-consistent imagery.

Reference-guided Controllable Inpainting of Neural Radiance Fields

The popularity of Neural Radiance Fields (NeRFs) for view synthesis has led to a desire for NeRF editing tools. Here, we focus on inpainting regions in a view-consistent and controllable manner. In addition to the typical NeRF inputs and masks delineating the unwanted region in each view, we require only a single inpainted view of the scene, i.e., a reference view. We use monocular depth estimators to back-project the inpainted view to the correct 3D positions. Then, via a novel rendering technique, a bilateral solver can construct view-dependent effects in non-reference views, making the inpainted region appear consistent from any view. For non-reference disoccluded regions, which cannot be supervised by the single reference view, we devise a method based on image inpainters to guide both the geometry and appearance. Our approach shows superior performance to NeRF inpainting baselines, with the additional advantage that a user can control the generated scene via a single inpainted image. Project page: https://ashmrz.github.io/reference-guided-3d