Recent work has shown that diffusion models can serve as powerful neural rendering engines that can be leveraged for inserting virtual objects into images. However, unlike typical physics-based renderers, these neural rendering engines are limited by the lack of manual control over the lighting, which is often essential for improving or personalizing the desired image outcome. In this paper, we show that precise and controllable lighting can be achieved without any additional training, simply by supplying a coarse shadow hint for the object. Indeed, we show that injecting only the desired shadow of the object into a pre-trained diffusionbased neural renderer enables it to accurately shade the object according to the desired light position, while properly harmonizing the object (and its shadow) within the target background image. Our method, SpotLight, is entirely training-free and leverages existing neural rendering approaches to achieve controllable relighting. We show that SpotLight achieves superior object compositing results, both quantitatively and perceptually, as confirmed by a user study, outperforming existing diffusion-based models specifically designed for relighting. We also demonstrate other applications, such as hand-scribbling shadows and full-image relighting, demonstrating its versatility.

Describing a scene in terms of primitives - geometrically simple shapes that offer a parsimonious but accurate abstraction of structure - is an established and difficult fitting problem. Different scenes require different numbers of primitives, and these primitives interact strongly. Existing methods are evaluated by comparing predicted depth, normals, and segmentation against ground truth. The state of the art method involves a learned regression procedure to predict a start point consisting of a fixed number of primitives, followed by a descent method to refine the geometry and remove redundant primitives. CSG (Constructive Solid Geometry) representations are significantly enhanced by a set-differencing operation. Our representation incorporates negative primitives, which are differenced from the positive primitives. These notably enrich the geometry that the model can encode, while complicating the fitting problem. This paper presents a method that can (a) incorporate these negative primitives and (b) choose the overall number of positive and negative primitives by ensembling. Extensive experiments on the standard NYUv2 dataset confirm that (a) this approach results in substantial improvements in depth representation and segmentation over SOTA and (b) negative primitives improve fitting accuracy. Our method is robustly applicable across datasets: in a first, we evaluate primitive prediction for LAION images.

We present UrbanIR (Urban Scene Inverse Rendering), a new inverse graphics model that enables realistic, free-viewpoint renderings of scenes under various lighting conditions with a single video. It accurately infers shape, albedo, visibility, and sun and sky illumination from wide-baseline videos, such as those from car-mounted cameras, differing from NeRF's dense view settings. In this context, standard methods often yield subpar geometry and material estimates, such as inaccurate roof representations and numerous ‘floaters’. UrbanIR addresses these issues with novel losses that reduce errors in inverse graphics inference and rendering artifacts. Its techniques allow for precise shadow volume estimation in the original scene. The model's outputs support controllable editing, enabling photorealistic free-viewpoint renderings of night simulations, relit scenes, and inserted objects, marking a significant improvement over existing state-of-the-art methods. Our code and data will be made publicly available upon acceptance.

Image-based relighting of indoor rooms creates an immersive virtual understanding of the space, which is useful for interior design, virtual staging, and real estate. Relighting indoor rooms from a single image is especially challenging due to complex illumination interactions between multiple lights and cluttered objects featuring a large variety in geometrical and material complexity. Recently, generative models have been successfully applied to imagebased relighting conditioned on a target image or a latent code, albeit without detailed local lighting control. In this paper, we introduce ScribbleLight, a generative model that supports local fine-grained control of lighting effects through scribbles that describe changes in lighting. Our key technical novelty is an Albedo-conditioned Stable Image Diffusion model that preserves the intrinsic color and texture of the original image after relighting and an encoder-decoder-based ControlNet architecture that enables geometry-preserving lighting effects with normal map and scribble annotations. We demonstrate ScribbleLight’s ability to create different lighting effects (e.g., turning lights on/off, adding highlights, cast shadows, or indirect lighting from unseen lights) from sparse scribble annotations.

We introduce LumiNet, a novel architecture that leverages generative models and latent intrinsic representations for transferring lighting from one image to another. Given a source image and a target lighting image, LumiNet generates a relit version of the source scene that captures the target’s lighting. Our approach makes two key contributions: a data curation strategy from the StyleGAN-based relighting model for our training, and a modified diffusion-based Con-trolNet that processes both latent intrinsic properties from the source image and latent extrinsic properties from the target image. We further improve lighting transfer through a learned adaptor that injects the target’s latent extrinsic properties via cross-attention and light-weight fine-tuning.Unlike traditional ControlNet, which generates images with conditional maps from a single scene, LumiNet processes latent representations from two different images -preserving geometry and albedo from the source while transferring lighting characteristics from the target. Experiments demonstrate that our method successfully transfers complex lighting phenomena including specular highlights and indirect illumination across scenes with varying spatial layouts and materials, outperforming existing approaches on challenging indoor scenes using only images as input.

This paper proposes a novel scene understanding task called Visual Jenga. Drawing inspiration from the game Jenga, the proposed task involves progressively removing objects from a single image until only the background remains. Just as Jenga players must understand structural dependencies to maintain tower stability, our task reveals the intrinsic relationships between scene elements by systematically exploring which objects can be removed while preserving scene coherence in both physical and geometric sense. As a starting point for tackling the Visual Jenga task, we propose a simple, data-driven, training-free approach that is surprisingly effective on a range of real-world images. The principle behind our approach is to utilize the asymmetry in the pairwise relationships between objects within a scene and employ a large inpainting model to generate a set of counterfactuals to quantify the asymmetry.

We present Zerocomp,an effective zero-shot 3D object compositing approach that does not require paired composite-scene images during training. Our method leverages ControlNet to condition from intrinsic images and combines it with a Stable Diffusion model to utilize its scene priors, together operating as an effective rendering engine. During training, Zerocompuses intrinsic images based on geometry, albedo, and masked shading, all without the need for paired images of scenes with and without compos-ite objects. Once trained, it seamlessly integrates virtual 3D objects into scenes, adjusting shading to create realistic composites. We develop a high-quality evaluation dataset and demonstrate that Zerocompoutperforms methods using explicit lighting estimations and generative techniques in quantitative and human perception benchmarks. Additionally, Zerocompextends to real and outdoor image compositing, even when trained solely on synthetic indoor data, showcasing its effectiveness in image compositing.

We describe a novel method, StyLitGAN, for relighting and resurfacing images in the absence of labeled data. StyL-itGAN generates images with realistic lighting effects, including cast shadows, soft shadows, inter-reflections, and glossy effects, without the need for paired or CGI data. StyLit-GAN uses an intrinsic image method to decompose an image, followed by a search of the latent space of a pretrained Style-GAN to identify a set of directions. By prompting the model to fix one component (e.g., albedo) and vary another (e.g., shading), we generate relighted images by adding the identi-fied directions to the latent style codes. Quantitative metrics of change in albedo and lighting diversity allow us to choose effective directions using a forward selection process. Qual-itative evaluation confirms the effectiveness of our method.

Generative models can produce impressively realistic images. This paper demonstrates that generated images have geometric features different from those of real images. We build a set of collections of generated images, prequalified to fool simple, signal-based classifiers into believing they are real. We then show that prequalified generated images can be identified reliably by classifiers that only look at geometric properties. We use three such classifiers. All three classifiers are denied access to image pixels, and look only at derived geometric features. The first classifier looks at the perspective field of the image, the second looks at lines detected in the image, and the third looks at relations between detected objects and shadows. Our procedure detects generated images more reliably than SOTA local signal based detectors, for images from a number of distinct generators. Saliency maps suggest that the classifiers can identify geometric problems reliably. We conclude that current generators cannot reliably reproduce geometric properties of real images.

Three-dimensional (3D) understanding of objects and scenes play a key role in humans' ability to interact with the world and has been an active area of research in computer vision, graphics, and robotics. Large scale synthetic and object-centric 3D datasets have shown to be effective in training models that have 3D understanding of objects. However, applying a similar approach to real-world objects and scenes is difficult due to a lack of large-scale data. Videos are a potential source for real-world 3D data, but finding diverse yet corresponding views of the same content have shown to be difficult at scale. Furthermore, standard videos come with fixed viewpoints, determined at the time of capture. This restricts the ability to access scenes from a variety of more diverse and potentially useful perspectives. We argue that large scale ODIN videos can address these limitations to provide scalable corresponding frames from diverse views. In this paper we introduce 360-1M, a 360° video dataset consisting of 1 million videos, and a process for efficiently finding corresponding frames from diverse viewpoints at scale. We train our diffusion-based model, ODIN, on 360-1M. Empowered by the largest real-world, multi-view dataset to date, ODIN is able to freely generate novel views of real-world scenes. Unlike previous methods, ODIN can move the camera through the environment, enabling the model to infer the geometry and layout of the scene. Additionally, we show improved performance on standard novel view synthesis and 3D reconstruction benchmarks.

Image relighting is the task of showing what a scene from a source image would look like if illuminated differently. Inverse graphic schemes recover an explicit representation of geometry and a set of chosen intrinsics, then relight with some form of renderer. But error control for inverse graphics is difficult, and inverse graphics methods can represent only the effects of the chosen intrinsics. This paper describes a relighting method that is entirely data-driven, where intrinsics and lighting are each represented as latent variables. Our approach produces SOTA relightings of real scenes, as measured by standard metrics. We show that albedo can be recovered from our latent intrinsics without using any example albedos, and that the albedos recovered are competitive with SOTA methods.

Dense depth and surface normal predictors should possess the equivariant property to cropping-and-resizing – cropping the input image should result in cropping the same output image. However, we find that state-of-the-art depth and normal predictors, despite having strong performances, surprisingly do not respect equivariance. The problem exists even when crop-and-resize data augmentation is employed during training. To remedy this, we propose an equivariant regularization technique, consisting of an averaging procedure and a self-consistency loss, to explicitly promote cropping-and-resizing equivariance in depth and normal networks. Our approach can be applied to both CNN and Transformer architectures, does not incur extra cost during testing, and notably improves the supervised and semi-supervised learning performance of dense predictors on Taskonomy tasks. Finally, finetuning with our loss on unlabeled images improves not only equivariance but also accuracy of state-of-the-art depth and normal predictors when evaluated on NYU-v2.

Intrinsic images, in the original sense, are image-like maps of scene properties like depth, normal, albedo, or shading. This paper demonstrates that StyleGAN can easily be induced to produce intrinsic images. The procedure is straightforward. We show that if StyleGAN produces $G({\bf w})$ from latent ${\bf w}$, then for each type of intrinsic image, there is a fixed offset ${\bf d}_c$ so that $G({\bf w}+{\bf d}_c)$ is that type of intrinsic image for $G({\bf w})$. Here ${\bf d}_c$ is {\em independent of ${\bf w}$}. The StyleGAN we used was pretrained by others, so this property is not some accident of our training regime. We show that there are image transformations StyleGAN will {\em not} produce in this fashion, so StyleGAN is not a generic image regression engine. It is conceptually exciting that an image generator should ``know'' and represent intrinsic images. There may also be practical advantages to using a generative model to produce intrinsic images. The intrinsic images obtained from StyleGAN compare well both qualitatively and quantitatively with those obtained by using SOTA image regression techniques; but StyleGAN's intrinsic images are robust to relighting effects, unlike SOTA methods.

Existing image editing tools, while powerful, typically disregard the underlying 3D geometry from which the image is projected. As a result, edits made using these tools may become detached from the geometry and lighting conditions that are at the foundation of the image formation process; such edits break the portrayal of a coherent 3D world. 3D-aware generative models are a promising solution, but currently only succeed on small datasets or at the level of a single object. In this work, we formulate the new task of language-guided 3D-aware editing, where objects in an image should be edited according to a language instruction while remaining consistent with the underlying 3D scene. To promote progress towards this goal, we release OBJect: a benchmark dataset of 400K editing examples created from procedurally generated 3D scenes. Each example consists of an input image, editing instruction in language, and the edited image. We also introduce 3DIT: single and multi-task models for four editing tasks. Our models show impressive abilities to understand the 3D composition of entire scenes, factoring in surrounding objects, surfaces, lighting conditions, shadows, and physically-plausible object configurations. Surprisingly, training on only synthetic scenes from \dataset, editing capabilities of 3DIT generalize to real-world images.

We show how to insert an object from one image to another and get realistic results in the hard case, where the shading of the inserted object clashes with the shading of the scene. Rendering objects using an illumination model of the scene doesn't work, because doing so requires a geometric and material model of the object, which is hard to recover from a single image. In this paper, we introduce a method that corrects shading inconsistencies of the inserted object without requiring a geometric and physical model or an environment map. Our method uses a deep image prior (DIP), trained to produce reshaded renderings of inserted objects via consistent image decomposition inferential losses. The resulting image from DIP aims to have (a) an albedo similar to the cut-and-paste albedo, (b) a similar shading field to that of the target scene, and (c) a shading that is consistent with the cut-and-paste surface normals. The result is a simple procedure that produces convincing shading of the inserted object. We show the efficacy of our method both qualitatively and quantitatively for several objects with complex surface properties and also on a dataset of spherical lampshades for quantitative evaluation. Our method significantly outperforms an Image Harmonization (IH) baseline for all these objects. They also outperform the cut-and-paste and IH baselines in a user study with over 100 users.

DIVeR builds on the key ideas of NeRF and its variants-density models and volume rendering – to learn 3D object models that can be rendered realistically from small numbers of images. In contrast to all previous NeRF methods, DIVeR uses deterministic rather than stochastic estimates of the volume rendering integral. DIVeR's representation is a voxel based field of features. To compute the volume rendering integral, a ray is broken into intervals, one per voxel; components of the volume rendering integral are estimated from the features for each interval using an MLP, and the components are aggregated. As a result, DIVeR can render thin translucent structures that are missed by other integrators. Furthermore, DIVeR's representation has semantics that is relatively exposed compared to other such methods – moving feature vectors around in the voxel space results in natural edits. Extensive qualitative and quantitative comparisons to current state-of-the-art methods show that DIVeR produces models that (1) render at or above state-of-the-art quality, (2) are very small without being baked, (3) render very fast without being baked, and (4) can be edited in natural ways. Our real-time code is available at: https://github.com/lwwu2/diver-rt

Humans can easily infer the underlying 3D geometry and texture of an object only from a single 2D image. Current computer vision methods can do this, too, but suffer from view generalization problems – the models inferred tend to make poor predictions of appearance in novel views. As for generalization problems in machine learning, the difficulty is balancing single-view accuracy (cf. training error; bias) with novel view accuracy (cf. test error; variance). We describe a class of models whose geometric rigidity is easily controlled to manage this tradeoff. We describe a cycle consistency loss that improves view generalization (roughly, a model from a generated view should predict the original view well). View generalization of textures requires that models share texture information, so a car seen from the back still has headlights because other cars have headlights. We describe a cycle consistency loss that encourages model textures to be aligned, so as to encourage sharing. We compare our method against the state-of-the-art method and show both qualitative and quantitative improvements.

Style transfer produces a transferred image which is a rendering of a content image in the manner of a style image. We seek to understand how to improve style transfer.To do so requires quantitative evaluation procedures, but current evaluation is qualitative, mostly involving user studies. We describe a novel quantitative evaluation procedure. Our procedure relies on two statistics: the Effectiveness (E) statistic measures the extent that a given style has been transferred to the target, and the Coherence (C) statistic measures the extent to which the original image's content is preserved. Our statistics are calibrated to human preference: targets with larger values of E and C will reliably be preferred by human subjects in comparisons of style and content, respectively.We use these statistics to investigate relative performance of a number of Neural Style Transfer (NST) methods, revealing a number of intriguing properties. Admissible methods lie on a Pareto frontier (i.e. improving E reduces C, or vice versa). Three methods are admissible: Universal style transfer produces very good C but weak E; modifying the optimization used for Gatys' loss produces a method with strong E and strong C; and a modified cross-layer method has slightly better E at strong cost in C. While the histogram loss improves the E statistics of Gatys' method, it does not make the method admissible. Surprisingly, style weights have relatively little effect in improving EC scores, and most variability in transfer is explained by the style itself (meaning experimenters can be misguided by selecting styles). Our GitHub Link is available1.