LiDAR-captured point clouds are often considered the gold standard in active 3D reconstruction. While their accuracy is exceptional in flat regions, the capturing is susceptible to missing small geometric structures, thin edges, and structures exhibiting challenging surface properties. Alternatively, capturing multiple photos of the scene and applying 3D photogrammetry can infer these details as they often represent feature-rich regions. However, the accuracy of LiDAR for featureless regions is rarely reached. Therefore, we suggest combining the strengths of LiDAR and camera-based capture by introducing SurfFill: a Gaussian surfel-based LiDAR completion scheme. We analyze LiDAR capturings and attribute LiDAR beam divergence as a main factor for artifacts, manifesting mostly at thin structures and edges. We use this insight to introduce an ambiguity heuristic for completed scans by evaluating the change in density in the point cloud. This allows us to identify points close to missed areas, which we can then use to grow additional points from to complete the scan. For this point growing, we employ Gaussian surfels and focus optimization and densification on these ambiguous areas. Finally, Gaussian primitives of the reconstruction in ambiguous areas are extracted and sampled for points to complete the point cloud. To address the challenges of large-scale reconstruction, we extend this pipeline with a divide-and-conquer scheme for building-sized point cloud completion. We evaluate on the task of LiDAR point cloud completion of synthetic and real-world scenes and find that our method outperforms previous reconstruction methods.

Abstract 3D Gaussian Splatting (3DGS) [KKLD23] has transformed novel‐view synthesis from RGB images, yet remains restricted to the visible spectrum. Many applications, including agricultural monitoring, rely on multi‐spectral imaging, where spectral camera alignment and scalability pose major challenges. We present MS‐Splatting—a multi‐spectral 3DGS framework enabling unified multi‐view consistent reconstruction and rendering across both visible and invisible spectra. Our key component is a neural color representation that encodes per‐primitive features shared across spectral bands, decoded through a shallow multi‐layer perceptron into spectrum‐specific radiance. By leveraging inter‐band correlations, this formulation enhances detail while reducing memory consumption compared to independent band modeling via per‐channel modeling with spherical harmonics. Our method enables accurate parallax‐free novel‐view vegetation index rendering for plant monitoring and enhances RGB novel view synthesis quality by exploiting details revealed through multi‐spectral bands. Our evaluation demonstrates that MS‐Splatting exceeds the current leading methods in both categories. In addition, we introduce a multi‐spectral dataset from aerial captures covering outdoor environments, specifically designed for evaluating these applications. We will release our code and dataset to facilitate further research. The project page is located at: https://meyerls.github.io/ms_splatting

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 Point‐based radiance field rendering has demonstrated impressive results for novel view synthesis, offering a compelling blend of rendering quality and computational efficiency. However, also latest approaches in this domain are not without their shortcomings. 3D Gaussian Splatting [KKLD23] struggles when tasked with rendering highly detailed scenes, due to blurring and cloudy artifacts. On the other hand, ADOP [RFS22] can accommodate crisper images, but the neural reconstruction network decreases performance, it grapples with temporal instability and it is unable to effectively address large gaps in the point cloud. In this paper, we present TRIPS (Trilinear Point Splatting), an approach that combines ideas from both Gaussian Splatting and ADOP. The fundamental concept behind our novel technique involves rasterizing points into a screen‐space image pyramid, with the selection of the pyramid layer determined by the projected point size. This approach allows rendering arbitrarily large points using a single trilinear write. A lightweight neural network is then used to reconstruct a hole‐free image including detail beyond splat resolution. Importantly, our render pipeline is entirely differentiable, allowing for automatic optimization of both point sizes and positions. Our evaluation demonstrate that TRIPS surpasses existing state‐of‐the‐art methods in terms of rendering quality while maintaining a real‐time frame rate of 60 frames per second on readily available hardware. This performance extends to challenging scenarios, such as scenes featuring intricate geometry, expansive landscapes, and auto‐exposed footage. The project page is located at: https://lfranke.github.io/trips

Existing real-time RGB-D reconstruction approaches, like Kinect Fusion, lack real-time photo-realistic visualization. This is due to noisy, oversmoothed or incomplete geometry and blurry textures which are fused from imperfect depth maps and camera poses. Recent neural rendering methods can overcome many of such artifacts but are mostly optimized for offline usage, hindering the integration into a live reconstruction pipeline.

In the last few years, deep neural networks opened the doors for big advances in novel view synthesis. Many of these approaches are based on a (coarse) proxy geometry obtained by structure from motion algorithms. Small deficiencies in this proxy can be fixed by neural rendering, but larger holes or missing parts, as they commonly appear for thin structures or for glossy regions, still lead to distracting artifacts and temporal instability. In this paper, we present a novel neural-rendering-based approach to detect and fix such deficiencies. As a proxy, we use a point cloud, which allows us to easily remove outlier geometry and to fill in missing geometry without complicated topological operations. Keys to our approach are (i) a differentiable, blending point-based renderer that can blend out redundant points, as well as (ii) the concept of Visual Error Tomography (VET), which allows us to lift 2D error maps to identify 3D-regions lacking geometry and to spawn novel points accordingly. Furthermore, (iii) by adding points as nested environment maps, our approach allows us to generate high-quality renderings of the surroundings in the same pipeline. In our results, we show that our approach can improve the quality of a point cloud obtained by structure from motion and thus increase novel view synthesis quality significantly. In contrast to point growing techniques, the approach can also fix large-scale holes and missing thin structures effectively. Rendering quality outperforms state-of-the-art methods and temporal stability is significantly improved, while rendering is possible at real-time frame rates.

Novel-view synthesis is an ill-posed problem in that it requires inference of previously unseen information. Recently, reviving the traditional field of image-based rendering, neural methods proved particularly suitable for this interpolation/extrapolation task; however, they often require a-priori scene-completeness or costly preprocessing steps and generally suffer from long (scene-specific) training times. Our work draws from recent progress in neural spatio-temporal supersampling to enhance a state-of-the-art neural renderer’s ability to infer novel-view information at inference time. We adapt a supersampling architecture [Xiao et al. 2020], which resamples previously rendered frames, to instead recombine nearby camera images in a multi-view dataset. These input frames are warped into a joint target frame, guided by the most recent (point-based) scene representation, followed by neural interpolation. The resulting architecture gains sufficient robustness to significantly improve transferability to previously unseen datasets. In particular, this enables novel applications for neural rendering where dynamically streamed content is directly incorporated in a (neural) image-based reconstruction of a scene. As we will show, our method reaches state-of-the-art performance when compared to previous works that rely on static and sufficiently densely sampled scenes; in addition, we demonstrate our system’s particular suitability for dynamically streamed content, where our approach is able to produce high-fidelity novel-view synthesis even with significantly fewer available frames than competing neural methods.

In this paper we present ADOP, a novel point-based, differentiable neural rendering pipeline. Like other neural renderers, our system takes as input calibrated camera images and a proxy geometry of the scene, in our case a point cloud. To generate a novel view, the point cloud is rasterized with learned feature vectors as colors and a deep neural network fills the remaining holes and shades each output pixel. The rasterizer renders points as one-pixel splats, which makes it very fast and allows us to compute gradients with respect to all relevant input parameters efficiently. Furthermore, our pipeline contains a fully differentiable physically-based photometric camera model, including exposure, white balance, and a camera response function. Following the idea of inverse rendering, we use our renderer to refine its input in order to reduce inconsistencies and optimize the quality of its output. In particular, we can optimize structural parameters like the camera pose, lens distortions, point positions and features, and a neural environment map, but also photometric parameters like camera response function, vignetting, and per-image exposure and white balance. Because our pipeline includes photometric parameters, e.g. exposure and camera response function, our system can smoothly handle input images with varying exposure and white balance, and generates high-dynamic range output. We show that due to the improved input, we can achieve high render quality, also for difficult input, e.g. with imperfect camera calibrations, inaccurate proxy geometry, or varying exposure. As a result, a simpler and thus faster deep neural network is sufficient for reconstruction. In combination with the fast point rasterization, ADOP achieves real-time rendering rates even for models with well over 100M points. https://github.com/darglein/ADOP

Abstract Rendering in real time for virtual reality headsets with high user immersion is challenging due to strict framerate constraints as well as due to a low tolerance for artefacts. Eye tracking‐based foveated rendering presents an opportunity to strongly increase performance without loss of perceived visual quality. To this end, we propose a novel foveated rendering method for virtual reality headsets with integrated eye tracking hardware. Our method comprises recycling pixels in the periphery by spatio‐temporally reprojecting them from previous frames. Artefacts and disocclusions caused by this reprojection are detected and re‐evaluated according to a confidence value that is determined by a newly introduced formalized perception‐based metric, referred to as confidence function. The foveal region, as well as areas with low confidence values, are redrawn efficiently, as the confidence value allows for the delicate regulation of hierarchical geometry and pixel culling. Hence, the average primitive processing and shading costs are lowered dramatically. Evaluated against regular rendering as well as established foveated rendering methods, our approach shows increased performance in both cases. Furthermore, our method is not restricted to static scenes and provides an acceleration structure for post‐processing passes.