Related papers: DeLiRa: Self-Supervised Depth, Light, and Radiance…
The goal of this work is to perform 3D reconstruction and novel view synthesis from data captured by scanning platforms commonly deployed for world mapping in urban outdoor environments (e.g., Street View). Given a sequence of posed RGB…
Photorealistic simulation plays a crucial role in applications such as autonomous driving, where advances in neural radiance fields (NeRFs) may allow better scalability through the automatic creation of digital 3D assets. However,…
This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distribution. This…
In this work we introduce a new self-supervised, semi-parametric approach for synthesizing novel views of a vehicle starting from a single monocular image. Differently from parametric (i.e. entirely learning-based) methods, we show how…
Modern-day display systems demand high-quality rendering. However, rendering at higher resolution requires a large number of data samples and is computationally expensive. Recent advances in deep learning-based image and video…
Dense and accurate 3D mapping from a monocular sequence is a key technology for several applications and still an open research area. This paper leverages recent results on single-view CNN-based depth estimation and fuses them with…
We present a method to synthesize novel views from a single $360^\circ$ panorama image based on the neural radiance field (NeRF). Prior studies in a similar setting rely on the neighborhood interpolation capability of multi-layer…
The task of novel view synthesis aims to generate unseen perspectives of an object or scene from a limited set of input images. Nevertheless, synthesizing novel views from a single image still remains a significant challenge in the realm of…
Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D descriptors for decoding novel views. However, existing…
Although significant progress has been made in room layout estimation, most methods aim to reduce the loss in the 2D pixel coordinate rather than exploiting the room structure in the 3D space. Towards reconstructing the room layout in 3D,…
Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. However, they neither fully exploit the 3D point-wise geometric correspondences, nor…
The ability to generate virtual environments is crucial for applications ranging from gaming to physical AI domains such as robotics, autonomous driving, and industrial AI. Current learning-based 3D reconstruction methods rely on the…
Generating novel views from recorded videos is crucial for enabling autonomous UAV navigation. Recent advancements in neural rendering have facilitated the rapid development of methods capable of rendering new trajectories. However, these…
We propose a differentiable rendering algorithm for efficient novel view synthesis. By departing from volume-based representations in favor of a learned point representation, we improve on existing methods more than an order of magnitude in…
We introduce a novel unsupervised approach to reconstructing a 3D volume from only two planar projections that exploits a previous\-ly-captured 3D volume of the patient. Such volume is readily available in many important medical procedures…
Modeling dynamic scenes is important for many applications such as virtual reality and telepresence. Despite achieving unprecedented fidelity for novel view synthesis in dynamic scenes, existing methods based on Neural Radiance Fields…
Depth-image-based rendering is a key view synthesis algorithm in 3D video systems, which enables the synthesis of virtual views from texture images and depth maps. An efficient view synthesis distortion estimation model is critical for…
Synthesizing novel views from a single view image is a highly ill-posed problem. We discover an effective solution to reduce the learning ambiguity by expanding the single-view view synthesis problem to a multi-view setting. Specifically,…
In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes. In our approach, a 3D scene is represented as a light field, i.e., a set of rays, each of which has a corresponding color…
Dense scene reconstruction for photo-realistic view synthesis has various applications, such as VR/AR, autonomous vehicles. However, most existing methods have difficulties in large-scale scenes due to three core challenges: \textit{(a)…