Related papers: DiffCSG: Differentiable CSG via Rasterization
Robotic cutting of soft materials is critical for applications such as food processing, household automation, and surgical manipulation. As in other areas of robotics, simulators can facilitate controller verification, policy learning, and…
Suboptimal color representation often hinders accurate image segmentation, yet many modern algorithms neglect this critical preprocessing step. This work presents a novel multidimensional nonlinear discriminant analysis algorithm,…
Image segmentation aims to partition an image according to the objects in the scene and is a fundamental step in analysing very high spatial-resolution (VHR) remote sensing imagery. Current methods struggle to effectively consider land…
Recently, several image segmentation methods that welcome and leverage different types of user assistance have been developed. In these methods, the user inputs can be provided by drawing bounding boxes over image objects, drawing scribbles…
3D Gaussian Splatting (3DGS) is increasingly attracting attention in both academia and industry owing to its superior visual quality and rendering speed. However, training a 3DGS model remains a time-intensive task, especially in load…
This paper presents a novel approach for the differentiable rendering of convex polyhedra, addressing the limitations of recent methods that rely on implicit field supervision. Our technique introduces a strategy that combines…
Physically based rendering of complex scenes can be prohibitively costly with a potentially unbounded and uneven distribution of complexity across the rendered image. The goal of an ideal level of detail (LoD) method is to make rendering…
We propose DiMeR, a novel geometry-texture disentangled feed-forward model with 3D supervision for sparse-view mesh reconstruction. Existing methods confront two persistent obstacles: (i) textures can conceal geometric errors, i.e.,…
Deep Gaussian processes (DGPs) provide a Bayesian non-parametric alternative to standard parametric deep learning models. A DGP is formed by stacking multiple GPs resulting in a well-regularized composition of functions. The Bayesian…
Recent probabilistic methods for 3D triangular meshes capture diverse shapes by differentiable mesh connectivity, but face high computational costs with increased shape details. We introduce a new differentiable mesh processing method that…
Rendering realistic images with global illumination is a computationally demanding task and often requires dedicated hardware for feasible runtime. Recent research uses Deep Neural Networks to predict indirect lighting on image level, but…
3D scene modeling techniques serve as the bedrocks in the geospatial engineering and computer science, which drives many applications ranging from automated driving, terrain mapping, navigation, virtual, augmented, mixed, and extended…
As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…
In real-world scenarios, environment changes caused by human or agent activities make it extremely challenging for robots to perform various long-term tasks. Recent works typically struggle to effectively understand and adapt to dynamic…
Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem as blurs arise not only from multiple object motions but also from camera shake, scene depth variation. To remove these complicated motion…
Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…
Simultaneous Localization and Mapping (SLAM) is pivotal in robotics, with photorealistic scene reconstruction emerging as a key challenge. To address this, we introduce Computational Alignment for Real-Time Gaussian Splatting SLAM (CaRtGS),…
Imitation learning-based visuomotor policies excel at manipulation tasks but often produce suboptimal action trajectories compared to model-based methods. Directly mapping camera data to actions via neural networks can result in jerky…
Differentiable renderers have been used successfully for unsupervised 3D structure learning from 2D images because they can bridge the gap between 3D and 2D. To optimize 3D shape parameters, current renderers rely on pixel-wise losses…
Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many recent works build on NeRF or 3D Gaussians, we…