We propose SparseFusion, a sparse view 3D reconstruction approach that unifies recent advances in neural rendering and probabilistic image generation. Existing approaches typically build on neural rendering with re-projected features but fail to generate unseen regions or handle uncertainty under large viewpoint changes. Alternate methods treat this as a (probabilistic) 2D synthesis task, and while they can generate plausible 2D images, they do not infer a consistent underlying 3D. However, we find that this trade-off between 3D consistency and probabilistic image generation does not need to exist. In fact, we show that geometric consistency and generative inference can be complementary in a mode-seeking behavior. By distilling a 3D consistent scene representation from a view-conditioned latent diffusion model, we are able to recover a plausible 3D representation whose renderings are both accurate and realistic. We evaluate our approach across 51 categories in the CO3D dataset and show that it outperforms existing methods, in both distortion and perception metrics, for sparse-view novel view synthesis.

We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models. While existing diffusion-based methods operate on images, latent codes, or point cloud data, we are the first to directly generate volumetric radiance fields. To this end, we propose a 3D denoising model which directly operates on an explicit voxel grid representation. However, as radiance fields generated from a set of posed images can be ambiguous and contain artifacts, obtaining ground truth radiance field samples is non-trivial. We address this challenge by pairing the denoising formulation with a rendering loss, enabling our model to learn a deviated prior that favours good image quality instead of trying to replicate fitting errors like floating artifacts. In contrast to 2D-diffusion models, our model learns multi-view consistent priors, enabling free-view synthesis and accurate shape generation. Compared to 3D GANs, our diffusion-based approach naturally enables conditional generation such as masked completion or single-view 3D synthesis at inference time.

2D-to-3D reconstruction is an ill-posed problem, yet humans are good at solving this problem due to their prior knowledge of the 3D world developed over years. Driven by this observation, we propose NeRDi, a single-view NeRF synthesis framework with general image priors from 2D diffusion models. Formulating single-view reconstruction as an image-conditioned 3D generation problem, we optimize the NeRF representations by minimizing a diffusion loss on its arbitrary view renderings with a pretrained image diffusion model under the input-view constraint. We leverage off-the-shelf vision-language models and introduce a two-section language guidance as conditioning inputs to the diffusion model. This is essentially helpful for improving multiview content coherence as it narrows down the general image prior conditioned on the semantic and visual features of the single-view input image. Additionally, we introduce a geometric loss based on estimated depth maps to regularize the underlying 3D geometry of the NeRF. Experimental results on the DTU MVS dataset show that our method can synthesize novel views with higher quality even compared to existing methods trained on this dataset. We also demonstrate our generalizability in zero-shot NeRF synthesis for in-the-wild images.

We address the challenge of recovering an underlying scene geometry and colors from a sparse set of RGBD view observations. In this work, we present a new solution that sequentially generates novel RGBD views along a camera trajectory, and the scene geometry is simply the fusion result of these views. More specifically, we maintain an intermediate surface mesh used for rendering new RGBD views, which subsequently becomes complete by an inpainting network; each rendered RGBD view is later back-projected as a partial surface and is supplemented into the intermediate mesh. The use of intermediate mesh and camera projection helps solve the refractory problem of multi-view inconsistency. We practically implement the RGBD inpainting network as a versatile RGBD diffusion model, which is previously used for 2D generative modeling; we make a modification to its reverse diffusion process to enable our use. We evaluate our approach on the task of 3D scene synthesis from sparse RGBD inputs; extensive experiments on the ScanNet dataset demonstrate the superiority of our approach over existing ones. Project page: https://jblei.site/project-pages/rgbd-diffusion.html

我们探索了基于神经光场表示的几种新颖观点合成的新策略。给定目标摄像头姿势，隐式神经网络将每个射线映射到其目标像素的颜色。该网络的条件是根据来自显式3D特征量的粗量渲染产生的本地射线特征。该卷是由使用3D Convnet的输入图像构建的。我们的方法在基于最先进的神经辐射场竞争方面，在合成和真实MVS数据上实现了竞争性能，同时提供了100倍的渲染速度。

Input: 3 views of held-out scene NeRF pixelNeRF Output: Rendered new views Input Novel views Input Novel views Input Novel views Figure 1: NeRF from one or few images. We present pixelNeRF, a learning framework that predicts a Neural Radiance Field (NeRF) representation from a single (top) or few posed images (bottom). PixelNeRF can be trained on a set of multi-view images, allowing it to generate plausible novel view synthesis from very few input images without test-time optimization (bottom left). In contrast, NeRF has no generalization capabilities and performs poorly when only three input views are available (bottom right).

计算机愿景中的经典问题是推断从几个可用于以交互式速率渲染新颖视图的图像的3D场景表示。以前的工作侧重于重建预定定义的3D表示，例如，纹理网格或隐式表示，例如隐式表示。辐射字段，并且通常需要输入图像，具有精确的相机姿势和每个新颖场景的长处理时间。在这项工作中，我们提出了场景表示变换器（SRT），一种方法，该方法处理新的区域的构成或未铺设的RGB图像，Infers Infers“设置 - 潜在场景表示”，并合成新颖的视图，全部在一个前馈中经过。为了计算场景表示，我们提出了视觉变压器的概括到图像组，实现全局信息集成，从而实现3D推理。一个有效的解码器变压器通过参加场景表示来参加光场以呈现新颖的视图。通过最大限度地减少新型视图重建错误，学习是通过最终到底的。我们表明，此方法在PSNR和Synthetic DataSets上的速度方面优于最近的基线，包括为纸张创建的新数据集。此外，我们展示了使用街景图像支持现实世界户外环境的交互式可视化和语义分割。

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 multiview 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

What is a rose, visually? A rose comprises its intrinsics, including the distribution of geometry, texture, and material specific to its object category. With knowledge of these intrinsic properties, we may render roses of different sizes and shapes, in different poses, and under different lighting conditions. In this work, we build a generative model that learns to capture such object intrinsics from a single image, such as a photo of a bouquet. Such an image includes multiple instances of an object type. These instances all share the same intrinsics, but appear different due to a combination of variance within these intrinsics and differences in extrinsic factors, such as pose and illumination. Experiments show that our model successfully learns object intrinsics (distribution of geometry, texture, and material) for a wide range of objects, each from a single Internet image. Our method achieves superior results on multiple downstream tasks, including intrinsic image decomposition, shape and image generation, view synthesis, and relighting.

自从神经辐射场（NERF）出现以来，神经渲染引起了极大的关注，并且已经大大推动了新型视图合成的最新作品。最近的重点是在模型上过度适合单个场景，以及学习模型的一些尝试，这些模型可以综合看不见的场景的新型视图，主要包括将深度卷积特征与类似NERF的模型组合在一起。我们提出了一个不同的范式，不需要深层特征，也不需要类似NERF的体积渲染。我们的方法能够直接从现场采样的贴片集中直接预测目标射线的颜色。我们首先利用表现几何形状沿着每个参考视图的异性线提取斑块。每个贴片线性地投影到1D特征向量和一系列变压器处理集合中。对于位置编码，我们像在光场表示中一样对射线进行参数化，并且至关重要的差异是坐标是相对于目标射线的规范化的，这使我们的方法与参考帧无关并改善了概括。我们表明，即使接受比先前的工作要少得多的数据训练，我们的方法在新颖的综合综合方面都超出了最新的视图综合。

由于其简单性和最先进的性能，神经辐射场（NERF）被出现为新型视图综合任务的强大表示。虽然NERF可以在许多输入视图可用时产生看不见的观点的光静观渲染，但是当该数量减少时，其性能显着下降。我们观察到，稀疏输入方案中的大多数伪像是由估计场景几何中的错误引起的，并且在训练开始时通过不同的行为引起。我们通过规范从未观察的视点呈现的修补程序的几何和外观来解决这一点，并在训练期间退火光线采样空间。我们还使用规范化的流模型来规范未观察的视点的颜色。我们的车型不仅优于优化单个场景的其他方法，而是在许多情况下，还有条件模型，这些模型在大型多视图数据集上广泛预先培训。

我们研究了从3D对象组成的场景的稀疏源观察的新型视图综合的问题。我们提出了一种简单但有效的方法，既不是持续的也不是隐含的，挑战近期观测综合的趋势。我们的方法将观察显式编码为启用摊销渲染的体积表示。我们证明，虽然由于其表现力，但由于其表现力，但由于其富有力的力量，我们的简单方法获得了与最新的基线的比较比较了与最先进的基线的相当甚至更好的新颖性重建质量，同时增加了渲染速度超过400倍。我们的模型采用类别无关方式培训，不需要特定于场景的优化。因此，它能够将新颖的视图合成概括为在训练期间未见的对象类别。此外，我们表明，通过简单的制定，我们可以使用视图综合作为自我监控信号，以便在没有明确的3D监督的情况下高效学习3D几何。

新型视图综合的古典光场渲染可以准确地再现视图依赖性效果，例如反射，折射和半透明，但需要一个致密的视图采样的场景。基于几何重建的方法只需要稀疏的视图，但不能准确地模拟非兰伯语的效果。我们介绍了一个模型，它结合了强度并减轻了这两个方向的局限性。通过在光场的四维表示上操作，我们的模型学会准确表示依赖视图效果。通过在训练和推理期间强制执行几何约束，从稀疏的视图集中毫无屏蔽地学习场景几何。具体地，我们介绍了一种基于两级变压器的模型，首先沿着ePipoll线汇总特征，然后沿参考视图聚合特征以产生目标射线的颜色。我们的模型在多个前进和360 {\ DEG}数据集中优于最先进的，具有较大的差别依赖变化的场景更大的边缘。

我们提出了HRF-NET，这是一种基于整体辐射场的新型视图合成方法，该方法使用一组稀疏输入来呈现新视图。最近的概括视图合成方法还利用了光辉场，但渲染速度不是实时的。现有的方法可以有效地训练和呈现新颖的观点，但它们无法概括地看不到场景。我们的方法解决了用于概括视图合成的实时渲染问题，并由两个主要阶段组成：整体辐射场预测指标和基于卷积的神经渲染器。该架构不仅基于隐式神经场的一致场景几何形状，而且还可以使用单个GPU有效地呈现新视图。我们首先在DTU数据集的多个3D场景上训练HRF-NET，并且网络只能仅使用光度损耗就看不见的真实和合成数据产生合理的新视图。此外，我们的方法可以利用单个场景的密集参考图像集来产生准确的新颖视图，而无需依赖其他明确表示，并且仍然保持了预训练模型的高速渲染。实验结果表明，HRF-NET优于各种合成和真实数据集的最先进的神经渲染方法。

Figure 1: Our method can synthesize novel views in both space and time from a single monocular video of a dynamic scene. Here we show video results with various configurations of fixing and interpolating view and time (left), as well as a visualization of the recovered scene geometry (right). Please view with Adobe Acrobat or KDE Okular to see animations.

We address the problem of synthesizing novel views from a monocular video depicting a complex dynamic scene. State-of-the-art methods based on temporally varying Neural Radiance Fields (aka dynamic NeRFs) have shown impressive results on this task. However, for long videos with complex object motions and uncontrolled camera trajectories, these methods can produce blurry or inaccurate renderings, hampering their use in real-world applications. Instead of encoding the entire dynamic scene within the weights of an MLP, we present a new approach that addresses these limitations by adopting a volumetric image-based rendering framework that synthesizes new viewpoints by aggregating features from nearby views in a scene-motion-aware manner. Our system retains the advantages of prior methods in its ability to model complex scenes and view-dependent effects, but also enables synthesizing photo-realistic novel views from long videos featuring complex scene dynamics with unconstrained camera trajectories. We demonstrate significant improvements over state-of-the-art methods on dynamic scene datasets, and also apply our approach to in-the-wild videos with challenging camera and object motion, where prior methods fail to produce high-quality renderings. Our project webpage is at dynibar.github.io.

我们提出了可推广的NERF变压器（GNT），这是一种纯粹的，统一的基于变压器的体系结构，可以从源视图中有效地重建神经辐射场（NERF）。与NERF上的先前作品不同，通过颠倒手工渲染方程来优化人均隐式表示，GNT通过封装两个基于变压器的阶段来实现可概括的神经场景表示和渲染。 GNT的第一阶段，称为View Transformer，利用多视图几何形状作为基于注意力的场景表示的电感偏差，并通过在相邻视图上从异性线中汇总信息来预测与坐标对齐的特征。 GNT的第二阶段，名为Ray Transformer，通过Ray Marching呈现新视图，并使用注意机制直接解码采样点特征的序列。我们的实验表明，当在单个场景上进行优化时，GNT可以在不明确渲染公式的情况下成功重建NERF，甚至由于可学习的射线渲染器，在复杂的场景上甚至将PSNR提高了〜1.3db。当在各种场景中接受培训时，GNT转移到前面的LLFF数据集（LPIPS〜20％，SSIM〜25％$）和合成搅拌器数据集（LPIPS〜20％，SSIM 〜25％$）时，GNN会始终达到最先进的性能4％）。此外，我们表明可以从学习的注意图中推断出深度和遮挡，这意味着纯粹的注意机制能够学习一个物理地面渲染过程。所有这些结果使我们更接近将变形金刚作为“通用建模工具”甚至用于图形的诱人希望。请参阅我们的项目页面以获取视频结果：https：//vita-group.github.io/gnt/。

This paper presents a 3D generative model that uses diffusion models to automatically generate 3D digital avatars represented as neural radiance fields. A significant challenge in generating such avatars is that the memory and processing costs in 3D are prohibitive for producing the rich details required for high-quality avatars. To tackle this problem we propose the roll-out diffusion network (Rodin), which represents a neural radiance field as multiple 2D feature maps and rolls out these maps into a single 2D feature plane within which we perform 3D-aware diffusion. The Rodin model brings the much-needed computational efficiency while preserving the integrity of diffusion in 3D by using 3D-aware convolution that attends to projected features in the 2D feature plane according to their original relationship in 3D. We also use latent conditioning to orchestrate the feature generation for global coherence, leading to high-fidelity avatars and enabling their semantic editing based on text prompts. Finally, we use hierarchical synthesis to further enhance details. The 3D avatars generated by our model compare favorably with those produced by existing generative techniques. We can generate highly detailed avatars with realistic hairstyles and facial hair like beards. We also demonstrate 3D avatar generation from image or text as well as text-guided editability.

Virtual reality and augmented reality (XR) bring increasing demand for 3D content. However, creating high-quality 3D content requires tedious work that a human expert must do. In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate the ability to generate a plausible 3D object with 360{\deg} views that correspond well with the given reference image. By conditioning on the reference image, our model can fulfill the everlasting curiosity for synthesizing novel views of objects from images. Our technique sheds light on a promising direction of easing the workflows for 3D artists and XR designers. We propose a novel framework, dubbed NeuralLift-360, that utilizes a depth-aware neural radiance representation (NeRF) and learns to craft the scene guided by denoising diffusion models. By introducing a ranking loss, our NeuralLift-360 can be guided with rough depth estimation in the wild. We also adopt a CLIP-guided sampling strategy for the diffusion prior to provide coherent guidance. Extensive experiments demonstrate that our NeuralLift-360 significantly outperforms existing state-of-the-art baselines. Project page: https://vita-group.github.io/NeuralLift-360/

在本文中，我们为复杂场景进行了高效且强大的深度学习解决方案。在我们的方法中，3D场景表示为光场，即，一组光线，每组在到达图像平面时具有相应的颜色。对于高效的新颖视图渲染，我们采用了光场的双面参数化，其中每个光线的特征在于4D参数。然后，我们将光场配向作为4D函数，即将4D坐标映射到相应的颜色值。我们训练一个深度完全连接的网络以优化这种隐式功能并记住3D场景。然后，特定于场景的模型用于综合新颖视图。与以前需要密集的视野的方法不同，需要密集的视野采样来可靠地呈现新颖的视图，我们的方法可以通过采样光线来呈现新颖的视图并直接从网络查询每种光线的颜色，从而使高质量的灯场呈现稀疏集合训练图像。网络可以可选地预测每光深度，从而使诸如自动重新焦点的应用。我们的小说视图合成结果与最先进的综合结果相当，甚至在一些具有折射和反射的具有挑战性的场景中优越。我们在保持交互式帧速率和小的内存占地面积的同时实现这一点。