Related papers: Efficient Scene Appearance Aggregation for Level-o…

We present a novel way of approaching image-based 3D reconstruction based on radiance fields. The problem of volumetric reconstruction is formulated as a non-linear least-squares problem and solved explicitly without the use of neural…

Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of features in a convolutional network, a layer in isolation is not…

Combining human body models with differentiable rendering has recently enabled animatable avatars of clothed humans from sparse sets of multi-view RGB videos. While state-of-the-art approaches achieve realistic appearance with neural…

With the emergence of neural radiance fields (NeRFs), view synthesis quality has reached an unprecedented level. Compared to traditional mesh-based assets, this volumetric representation is more powerful in expressing scene geometry but…

Combining accurate geometry with rich semantics has been proven to be highly effective for language-guided robotic manipulation. Existing methods for dynamic scenes either fail to update in real-time or rely on additional depth sensors for…

Rendering photo-realistic novel-view images of complex scenes has been a long-standing challenge in computer graphics. In recent years, great research progress has been made on enhancing rendering quality and accelerating rendering speed in…

We consider the problem of category-level 6D pose estimation from a single RGB image. Our approach represents an object category as a cuboid mesh and learns a generative model of the neural feature activations at each mesh vertex to perform…

Although 3D Gaussian Splatting (3D-GS) achieves efficient rendering for novel view synthesis, extending it to dynamic scenes still results in substantial memory overhead from replicating Gaussians across frames. To address this challenge,…

3D Gaussian Splatting (3DGS) has revolutionized 3D scene reconstruction, which effectively balances rendering quality, efficiency, and speed. However, existing 3DGS approaches usually generate plausible outputs and face significant…

NeRF provides unparalleled fidelity of novel view synthesis: rendering a 3D scene from an arbitrary viewpoint. NeRF requires training on a large number of views that fully cover a scene, which limits its applicability. While these issues…

We present 3D Surface Splatting (3DSS), the first differentiable surface splatting renderer for physically-based inverse rendering from multi-view images. Our central insight is that the surface separation problem at the heart of surface…

Achieving real-time and accuracy on embedded platforms has always been the pursuit of road segmentation methods. To this end, they have proposed many lightweight networks. However, they ignore the fact that roads are "stuff" (background or…

Modeling wave properties of light is an important milestone for advancing physically-based rendering. In this paper, we propose complex-valued holographic radiance fields, a method that optimizes scenes without relying on intensity-based…

We present SetDiff, a geometry-grounded multi-view diffusion framework that enhances novel-view renderings produced by 3D Gaussian Splatting. Our method integrates explicit 3D priors, pixel-aligned coordinate maps and pose-aware Plucker ray…

In the domain of 3D scene representation, 3D Gaussian Splatting (3DGS) has emerged as a pivotal technology. However, its application to large-scale, high-resolution scenes (exceeding 4k$\times$4k pixels) is hindered by the excessive…

This paper proposes a method to reconstruct the neural radiance field with equirectangular omnidirectional images. Implicit neural scene representation with a radiance field can reconstruct the 3D shape of a scene continuously within a…

We present a deep learning approach to reconstruct scene appearance from unstructured images captured under collocated point lighting. At the heart of Deep Reflectance Volumes is a novel volumetric scene representation consisting of…

Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-learning based methods yield good estimates of object poses,…

Typical inverse rendering methods focus on learning implicit neural scene representations by modeling the geometry, materials and illumination separately, which entails significant computations for optimization. In this work we design a…

We present a novel method of simulating wave effects in graphics using ray--based renderers with a new function: the Wave BSDF (Bidirectional Scattering Distribution Function). Reflections from neighboring surface patches represented by…