Related papers: Look Beyond: Two-Stage Scene View Generation via P…

NeRF aims to learn a continuous neural scene representation by using a finite set of input images taken from various viewpoints. A well-known limitation of NeRF methods is their reliance on data: the fewer the viewpoints, the higher the…

Synthesizing novel views for urban environments is crucial for tasks like autonomous driving and virtual tours. Compared to object-level or indoor situations, outdoor settings present unique challenges, such as inconsistency across frames…

We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks. MVGenMaster leverages 3D priors that are warped using metric depth and camera poses, significantly…

Novel view synthesis (NVS) is a challenging task in computer vision that involves synthesizing new views of a scene from a limited set of input images. Neural Radiance Fields (NeRF) have emerged as a powerful approach to address this…

We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image. This is a challenging problem that goes far beyond the capabilities of…

Realistic view extrapolation is critical for closed-loop simulation in autonomous driving, yet it remains a significant challenge for current Novel View Synthesis (NVS) methods, which often produce distorted and inconsistent images beyond…

Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods…

A concept of light-fields computed from multiple view images on regular grids has proven its benefit for scene representations, and supported realistic renderings of novel views and photographic effects such as refocusing and shallow depth…

This paper describes the Qualcomm AI Research solution to the RealADSim-NVS challenge, hosted at the RealADSim Workshop at ICCV 2025. The challenge concerns novel view synthesis in street scenes, and participants are required to generate,…

Despite recent successes in novel view synthesis using 3D Gaussian Splatting (3DGS), modeling scenes with sparse inputs remains a challenge. In this work, we address two critical yet overlooked issues in real-world sparse-input modeling:…

We explore novel-view synthesis for dynamic scenes from monocular videos. Prior approaches rely on costly test-time optimization of 4D representations or do not preserve scene geometry when trained in a feed-forward manner. Our approach is…

The view synthesis problem--generating novel views of a scene from known imagery--has garnered recent attention due in part to compelling applications in virtual and augmented reality. In this paper, we explore an intriguing scenario for…

We propose a new view synthesis method via synthesizing a 3D neural field from both single or few-view input images. To address the ill-posed nature of the image-to-3D generation problem, we devise a two-stage method that involves a…

Dynamic Novel View Synthesis aims to generate photorealistic views of moving subjects from arbitrary viewpoints. This task is particularly challenging when relying on monocular video, where disentangling structure from motion is ill-posed…

We present a generalizable novel view synthesis method which enables modifying the visual appearance of an observed scene so rendered views match a target weather or lighting condition without any scene specific training or access to…

We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view, where this capability is learned from a collection of single photographs, without requiring camera poses or even…

Generating consistent multi-view images from a single image remains challenging. Lack of spatial consistency often degrades 3D mesh quality in surface reconstruction. To address this, we propose LoomNet, a novel multi-view diffusion…

We present 3DiM, a diffusion model for 3D novel view synthesis, which is able to translate a single input view into consistent and sharp completions across many views. The core component of 3DiM is a pose-conditional image-to-image…

Reconstructing dynamic fluids from sparse views is a long-standing and challenging problem, due to the severe lack of 3D information from insufficient view coverage. While several pioneering approaches have attempted to address this issue…

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…