Related papers: Pulsar: Efficient Sphere-based Neural Rendering

Recent developments in differentiable and neural rendering have made impressive breakthroughs in a variety of 2D and 3D tasks, e.g. novel view synthesis, 3D reconstruction. Typically, differentiable rendering relies on a dense viewpoint…

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 propose a hybrid…

Recent advances in view synthesis and real-time rendering have achieved photorealistic quality at impressive rendering speeds. While Radiance Field-based methods achieve state-of-the-art quality in challenging scenarios such as in-the-wild…

Real-time rendering for video games has become increasingly challenging due to the need for higher resolutions, framerates and photorealism. Supersampling has emerged as an effective solution to address this challenge. Our work introduces a…

This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new…

Differentiable rendering techniques like Gaussian Splatting and Neural Radiance Fields have become powerful tools for generating high-fidelity models of 3D objects and scenes. Their ability to produce both physically plausible and…

This work introduces FlashGS, an open-source CUDA Python library, designed to facilitate the efficient differentiable rasterization of 3D Gaussian Splatting through algorithmic and kernel-level optimizations. FlashGS is developed based on…

High-resolution simulations often rely on the Adaptive Mesh Resolution (AMR) technique to optimize memory consumption versus attainable precision. While this technique allows for dramatic improvements in terms of computing performance, the…

Leveraging recent diffusion models, LiDAR-based large-scale 3D scene generation has achieved great success. While recent voxel-based approaches can generate both geometric structures and semantic labels, existing range-view methods are…

Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…

Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently…

Segmentation, a useful/powerful technique in pattern recognition, is the process of identifying object outlines within images. There are a number of efficient algorithms for segmentation in Euclidean space that depend on the variational…

3D scene understanding is a critical yet challenging task in autonomous driving due to the irregularity and sparsity of LiDAR data, as well as the computational demands of processing large-scale point clouds. Recent methods leverage…

Interactive dynamic simulators are an accelerator for developing novel robotic control algorithms and complex systems involving humans and robots. In user training and synthetic data generation applications, high-fidelity visualizations…

Static LiDAR scanners produce accurate, dense, colored point clouds, but often contain obtrusive artifacts which makes them ill-suited for direct display. We propose an efficient method to render photorealistic images of such scans without…

Convolutional Neural Networks (CNNs) are a cornerstone of the Deep Learning toolbox and have led to many breakthroughs in Artificial Intelligence. These networks have mostly been developed for regular Euclidean domains such as those…

Recent advances in novel view synthesis have demonstrated impressive results in fast photorealistic scene rendering through differentiable point rendering, either via Gaussian Splatting (3DGS) [Kerbl and Kopanas et al. 2023] or neural point…

Neural radiance fields provide state-of-the-art view synthesis quality but tend to be slow to render. One reason is that they make use of volume rendering, thus requiring many samples (and model queries) per ray at render time. Although…

This paper addresses the limitations of neural rendering-based multi-view surface reconstruction methods, which require an additional mesh extraction step that is inconvenient and would produce poor-quality surfaces with mesh aliasing,…

Rendering high-fidelity images from sparse point clouds is still challenging. Existing learning-based approaches suffer from either hole artifacts, missing details, or expensive computations. In this paper, we propose a novel framework to…