Related papers: Structure-Aware Parametric Representations for Tim…
Implicit Neural Representation for Videos (NeRV) has introduced a novel paradigm for video representation and compression, outperforming traditional codecs. As model size grows, however, slow encoding and decoding speed and high memory…
We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach,…
While sensing in high temporal resolution is necessary for wide range of application, it is still limited nowadays due to cameras sampling rate. In this work we try to increase the temporal resolution beyond the Nyquist frequency, which is…
We present GI-GS, a novel inverse rendering framework that leverages 3D Gaussian Splatting (3DGS) and deferred shading to achieve photo-realistic novel view synthesis and relighting. In inverse rendering, accurately modeling the shading…
The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…
This paper suggests a nonparametric scheme to find the sparse solution of the underdetermined system of linear equations in the presence of unknown impulsive or non-Gaussian noise. This approach is robust against any variations of the noise…
3D surface reconstruction is essential across applications of virtual reality, robotics, and mobile scanning. However, RGB-based reconstruction often fails in low-texture, low-light, and low-albedo scenes. Handheld LiDARs, now common on…
Modeling reflections from 2D images is essential for photorealistic rendering and novel view synthesis. Recent approaches enhance Gaussian primitives with reflection-related material attributes to enable physically based rendering (PBR)…
This paper focuses on scene reconstruction under nighttime conditions in autonomous driving simulation. Recent methods based on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) have achieved photorealistic modeling in…
Searching for a unified scene representation remains a research challenge in computer graphics. Traditional mesh-based representations are unsuitable for dense, fuzzy elements, and introduce additional complexity for filtering and…
We propose a real-time method to estimate spatiallyvarying indoor lighting from a single RGB image. Given an image and a 2D location in that image, our CNN estimates a 5th order spherical harmonic representation of the lighting at the given…
Accurate geometric surface reconstruction, providing essential environmental information for navigation and manipulation tasks, is critical for enabling robotic self-exploration and interaction. Recently, 3D Gaussian Splatting (3DGS) has…
While 3D Gaussian splatting has emerged as a powerful paradigm, it fundamentally fails to model transparency such as glass panels. The core challenge lies in decoupling the intertwined radiance contributions from transparent interfaces and…
Although low-rank and sparse decomposition based methods have been successfully applied to the problem of moving object detection using structured sparsity-inducing norms, they are still vulnerable to significant illumination changes that…
In this paper, we characterize data-time tradeoffs of the proximal-gradient homotopy method used for solving linear inverse problems under sub-Gaussian measurements. Our results are sharp up to an absolute constant factor. We demonstrate…
The introduction of 3D Gaussian Splatting (3DGS) has advanced novel view synthesis by utilizing Gaussians to represent scenes. Encoding Gaussian point features with anchor embeddings has significantly enhanced the performance of newer 3DGS…
Traditional vision-based autonomous driving systems often face difficulties in navigating complex environments when relying solely on single-image inputs. To overcome this limitation, incorporating temporal data such as past image frames or…
3D Gaussian Splatting has shown remarkable capabilities in novel view rendering tasks and exhibits significant potential for multi-view optimization.However, the original 3D Gaussian Splatting lacks color representation for inputs in…
Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination. We wish to endow robots with this same capability. In this paper, we tackle the challenge of…
In many applications it is important to estimate a fluid flow field from limited and possibly corrupt measurements. Current methods in flow estimation often use least squares regression to reconstruct the flow field, finding the…