相关论文: TREVR2: Illuminating fast $N\log_2\,N$ radiative t…

Interactions between clouds and radiation are at the root of many difficulties in numerically predicting future weather and climate and in retrieving the state of the atmosphere from remote sensing observations. The large range of issues…

To facilitate the study of black hole fueling, star formation, and feedback in galaxies, we outline a method for treating the radial forces on interstellar gas due to absorption of photons by dust grains. The method gives the correct…

Inference problems in graphical models are often approximated by casting them as constrained optimization problems. Message passing algorithms, such as belief propagation, have previously been suggested as methods for solving these…

Reinforcement learning with stochastic optimal control offers a promising framework for diffusion fine-tuning, where a pre-trained diffusion model is optimized to generate paths that lead to a reward-tilted distribution. While these…

This paper presents a novel grid-based NeRF called F2-NeRF (Fast-Free-NeRF) for novel view synthesis, which enables arbitrary input camera trajectories and only costs a few minutes for training. Existing fast grid-based NeRF training…

In this paper, we consider a tree inference problem motivated by the critical problem in single-cell genomics of reconstructing dynamic cellular processes from sequencing data. In particular, given a population of cells sampled from such a…

We simulate convection near the solar surface, where the continuum optical depth is of order unity. Hence, to determine the radiative heating and cooling in the energy conservation equation, we must solve the radiative transfer equation…

We present Mesh2NeRF, an approach to derive ground-truth radiance fields from textured meshes for 3D generation tasks. Many 3D generative approaches represent 3D scenes as radiance fields for training. Their ground-truth radiance fields are…

We present two types of numerical prescriptions that accelerate the radiative transfer calculation around point sources within a three-dimensional Cartesian grid by using the oct-tree structure for the distribution of radiation sources. In…

Neural radiance fields (NeRF) has gained significant attention for its exceptional visual effects. However, most existing NeRF methods reconstruct 3D scenes from RGB images captured by visible light cameras. In practical scenarios like…

Recent advances in Neural Radiance Fields (NeRF) have demonstrated significant potential for representing 3D scene appearances as implicit neural networks, enabling the synthesis of high-fidelity novel views. However, the lengthy training…

Speculative decoding is a promising approach for accelerating large language models. The primary idea is to use a lightweight draft model to speculate the output of the target model for multiple subsequent timesteps, and then verify them in…

Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks. Various neural network models are proposed to learn from tree-structured program representations, e.g.,…

In this work, we introduce a fast numerical algorithm to solve the time-dependent radiative transport equation (RTE). Our method uses the integral formulation of RTE and applies the treecode algorithm to reduce the computational complexity…

This paper proposes a novel approach for rendering a pre-trained Neural Radiance Field (NeRF) in real-time on resource-constrained devices. We introduce Re-ReND, a method enabling Real-time Rendering of NeRFs across Devices. Re-ReND is…

We present a new approach to numerically model continuum radiative transfer based on the Optically Thin Variable Eddington Tensor (OTVET) approximation. Our method insures the exact conservation of the photon number and flux (in the…

We present a new method for estimating the Neural Reflectance Field (NReF) of an object from a set of posed multi-view images under unknown lighting. NReF represents 3D geometry and appearance of objects in a disentangled manner, and are…

The mutual intensity and its equivalent phase-space representations quantify an optical field's state of coherence and are important tools in the study of light propagation and dynamics, but they can only be estimated indirectly from…

We present RAYTHEIA, a high-performance reverse ray-tracing algorithm designed to efficiently solve three-dimensional direction-dependent equations in astronomical simulations. The algorithm uses a dual-grid framework in which the native…

Physics-based inverse rendering enables joint optimization of shape, material, and lighting based on captured 2D images. To ensure accurate reconstruction, using a light model that closely resembles the captured environment is essential.…