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.

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.

Rendering for Head Mounted Displays (HMD) causes a doubled computational effort, since serving the human stereopsis requires the creation of one image for the left and one for the right eye. The difference in this image pair, called binocular disparity, is an important cue for depth perception and the spatial arrangement of surrounding objects. Findings in the context of the human visual system (HVS) have shown that especially in the near range of an observer, binocular disparities have a high significance. But as with rising distance the disparity converges to a simple geometric shift, also the importance as depth cue exponentially declines. In this paper, we exploit this knowledge about the human perception by rendering objects fully stereoscopic only up to a chosen distance and monoscopic, from there on. By doing so, we obtain three distinct images which are synthesized to a new hybrid stereoscopic image pair, which reasonably approximates a conventionally rendered stereoscopic image pair. The method has the potential to reduce the amount of rendered primitives easily to nearly 50 % and thus, significantly lower frame times. Besides of a detailed analysis of the introduced formal error and how to deal with occurring artifacts, we evaluated the perceived quality of the VR experience during a comprehensive user study with nearly 50 participants. The results show that the perceived difference in quality between the shown image pairs was generally small. An in-depth analysis is given on how the participants reached their decisions and how they subjectively rated their VR experience.