We introduce a new approach for reconstruction and novel view synthesis of unbounded real-world scenes. In contrast to previous methods using either volumetric fields, grid-based models, or discrete point cloud proxies, we pro-pose a hybrid scene representation, which implicitly encodes the geometry in a continuous octree-based probability field and view-dependent appearance in a multi-resolution hash grid. This allows for extraction of arbitrary explicit point clouds, which can be rendered using rasterization. In doing so, we combine the benefits of both worlds and retain favorable behavior during optimization: Our novel implicit point cloud representation and differentiable bilinear rasterizer enable fast rendering while preserving the fine geometric detail captured by volumetric neural fields. Furthermore, this representation does not depend on priors like structure-from-motion point clouds. Our method achieves state-of-the-art image quality on common benchmarks. Furthermore, we achieve fast inference at interactive frame rates, and can convert our trained model into a large, explicit point cloud to further enhance performance.

Abstract 3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real‐time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for robust convergence of a scene reconstruction or for artifact‐free fly‐throughs. Recent work started mitigating artifacts that break multi‐view coherence, including popping artifacts due to inconsistent transparency sorting and perspective‐correct outlines of (2D) splats. At the same time, real‐time requirements forced such implementations to accept compromises in how transparency of large assemblies of 3D Gaussians is resolved, in turn breaking coherence in other ways. In our work, we aim at achieving maximum coherence, by rendering fully perspective‐correct 3D Gaussians while using a high‐quality approximation of accurate blending, hybrid transparency, on a per‐pixel level, in order to retain real‐time frame rates. Our fast and perspectively accurate approach for evaluation of 3D Gaussians does not require matrix inversions, thereby ensuring numerical stability and eliminating the need for special handling of degenerate splats, and the hybrid transparency formulation for blending maintains similar quality as fully resolved per‐pixel transparencies at a fraction of the rendering costs. We further show that each of these two components can be independently integrated into Gaussian splatting systems. In combination, they achieve up to 2× higher frame rates, 2× faster optimization, and equal or better image quality with fewer rendering artifacts compared to traditional 3DGS on common benchmarks.

Abstract Dynamic reconstruction and spatiotemporal novel‐view synthesis of non‐rigidly deforming scenes recently gained increased attention. While existing work achieves impressive quality and performance on multi‐view or teleporting camera setups, most methods fail to efficiently and faithfully recover motion and appearance from casual monocular captures. This paper contributes to the field by introducing a new method for dynamic novel view synthesis from monocular video, such as casual smartphone captures. Our approach represents the scene as a dynamic neural point cloud, an implicit time‐conditioned point distribution that encodes local geometry and appearance in separate hash‐encoded neural feature grids for static and dynamic regions. By sampling a discrete point cloud from our model, we can efficiently render high‐quality novel views using a fast differentiable rasterizer and neural rendering network. Similar to recent work, we leverage advances in neural scene analysis by incorporating data‐driven priors like monocular depth estimation and object segmentation to resolve motion and depth ambiguities originating from the monocular captures. In addition to guiding the optimization process, we show that these priors can be exploited to explicitly initialize our scene representation to drastically improve optimization speed and final image quality. As evidenced by our experimental evaluation, our dynamic point cloud model not only enables fast optimization and real‐time frame rates for interactive applications, but also achieves competitive image quality on monocular benchmark sequences. Our code and data are available online https://moritzkappel.github.io/projects/dnpc/ .

The reconstruction and novel view synthesis of dynamic scenes recently gained increased attention. As reconstruction from large-scale multi-view data involves immense memory and computational requirements, recent benchmark datasets provide collections of single monocular views per timestamp sampled from multiple (virtual) cameras. We refer to this form of inputs asmonocularizeddata. Existing work shows impressive results for synthetic setups and forward-facing real-world data, but is often limited in the training speed and angular range for generating novel views. This paper addresses these limitations and proposes a new method for full$360^{\circ}$inward-facing novel view synthesis of non-rigidly deforming scenes. At the core of our method are: 1) An efficient deformation module that decouples the processing of spatial and temporal information for accelerated training and inference; and 2) A static module representing the canonical scene as a fast hash-encoded neural radiance field. In addition to existing synthetic monocularized data, we systematically analyze the performance on real-world inward-facing scenes using a newly recorded challenging dataset sampled from a synchronized large-scale multi-view rig. In both cases, our method is significantly faster than previous methods, converging in less than 7 minutes and achieving real-time framerates at 1K resolution, while obtaining a higher visual accuracy for generated novel views. Our code and dataset are available online:https://github.com/MoritzKappel/MoNeRF.

Abstract In this paper, we tackle the challenging problem of rendering real‐world 360° panorama videos that support full 6 degrees‐of‐freedom (DoF) head motion from a prerecorded omnidirectional stereo (ODS) video. In contrast to recent approaches that create novel views for individual panorama frames, we introduce a video‐specific temporally‐consistent multi‐sphere image (MSI) scene representation. Given a conventional ODS video, we first extract information by estimating framewise descriptive feature maps. Then, we optimize the global MSI model using theory from recent research on neural radiance fields. Instead of a continuous scene function, this multi‐sphere image (MSI) representation depicts colour and density information only for a discrete set of concentric spheres. To further improve the temporal consistency of our results, we apply an ancillary refinement step which optimizes the temporal coherency between successive video frames. Direct comparisons to recent baseline approaches show that our global MSI optimization yields superior performance in terms of visual quality. Our code and data will be made publicly available.

Video-based human motion transfer creates video animations of humans following a source motion. Current methods show remarkable results for tightly-clad subjects. However, the lack of temporally consistent handling of plausible clothing dynamics, including fine and high-frequency details, significantly limits the attainable visual quality. We address these limitations for the first time in the literature and present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations, for several types of loose garments. In contrast to the previous techniques, we perform image generation in three subsequent stages: synthesizing human shape, structure, and appearance. Given a monocular RGB video of an actor, we train a stack of recurrent deep neural networks that generate these intermediate representations from 2D poses and their temporal derivatives. Splitting the difficult motion transfer problem into subtasks that are aware of the temporal motion context helps us to synthesize results with plausible dynamics and pose-dependent detail. It also allows artistic control of results by manipulation of individual framework stages. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism. The source code is available at https://graphics.tu-bs.de/publications/kappel2020high-fidelity.

We present a new pipeline to enable head-motion parallax in omnidirectional stereo (ODS) panorama video rendering using a neural depth decoder. While recent ODS panorama cameras record short-baseline horizontal stereo parallax to offer the impression of binocular depth, they do not support the necessary translational degrees-of-freedom (DoF) to also provide for head-motion parallax in virtual reality (VR) applications.