Related papers: YoNoSplat: You Only Need One Model for Feedforward…
Visuomotor policies learned from teleoperated demonstrations face challenges such as lengthy data collection, high costs, and limited data diversity. Existing approaches address these issues by augmenting image observations in RGB space or…
3D Gaussian Splatting (3DGS) has recently unlocked real-time, high-fidelity novel view synthesis by representing scenes using explicit 3D primitives. However, traditional methods often require millions of Gaussians to capture complex…
We introduce the \method, an ultra-efficient approach for monocular 3D object reconstruction. Splatter Image is based on Gaussian Splatting, which allows fast and high-quality reconstruction of 3D scenes from multiple images. We apply…
Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric cases. In…
Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily…
Dynamic scene reconstruction represents a fundamental yet demanding challenge in computer vision and robotics. While recent progress in 3DGS-based methods has advanced dynamic scene modeling, obtaining high-fidelity rendering and accurate…
We introduce OceanSplat, a novel 3D Gaussian Splatting-based approach for high-fidelity underwater scene reconstruction. To overcome multi-view inconsistencies caused by scattering media, we design a trinocular setup for each camera pose by…
Real-time reconstruction of dynamic 3D scenes from uncalibrated video streams demands robust online methods that recover scene dynamics from sparse observations under strict latency and memory constraints. Yet most dynamic reconstruction…
Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more. Existing approaches based on volumetric rendering obtain promising results, but optimize on a…
We propose ActiveSplat, an autonomous high-fidelity reconstruction system leveraging Gaussian splatting. Taking advantage of efficient and realistic rendering, the system establishes a unified framework for online mapping, viewpoint…
Reconstructing deformable tissues from endoscopic videos is essential in many downstream surgical applications. However, existing methods suffer from slow rendering speed, greatly limiting their practical use. In this paper, we introduce…
The semantic synthesis of unseen scenes from multiple viewpoints is crucial for research in 3D scene understanding. Current methods are capable of rendering novel-view images and semantic maps by reconstructing generalizable Neural Radiance…
Novel-view synthesis and 3D reconstruction from sparse posed images are central to robotics and AR/VR. Yet, feed-forward 3D Gaussian reconstruction fails under lowlight due to noise, color shifts, and unreliable correspondence. We propose…
Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details.…
We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a "foundation" model for monocular depth estimation and…
Reconstructing large-scale dynamic driving scenes remains challenging due to the coexistence of static environments with extreme depth variation and diverse dynamic actors exhibiting complex motions. Existing Gaussian Splatting based…
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…
We introduce MVSplat360, a feed-forward approach for 360{\deg} novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and…
We present a framework that enables fast reconstruction and real-time rendering of urban-scale scenes while maintaining robustness against appearance variations across multi-view captures. Our approach begins with scene partitioning for…
The recent advent of 3D Gaussian Splatting (3DGS) has revolutionized the 3D scene reconstruction space enabling high-fidelity novel view synthesis in real-time. However, with the exception of RawNeRF, all prior 3DGS and NeRF-based methods…