Related papers: FreeVS: Generative View Synthesis on Free Driving …
We propose FreeSim, a camera simulation method for autonomous driving. FreeSim emphasizes high-quality rendering from viewpoints beyond the recorded ego trajectories. In such viewpoints, previous methods have unacceptable degradation…
Driving view synthesis along free-form trajectories is essential for realistic driving simulations, enabling closed-loop evaluation of end-to-end driving policies. Existing methods excel at view interpolation along recorded paths but…
Recent 3D novel view synthesis (NVS) methods often require extensive 3D data for training, and also typically lack generalization beyond the training distribution. Moreover, they tend to be object centric and struggle with complex and…
Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…
A fundamental bottleneck in Novel View Synthesis (NVS) for autonomous driving is the inherent supervision gap on novel trajectories: models are tasked with synthesizing unseen views during inference, yet lack ground truth images for these…
The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…
Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory observations, limiting…
Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are…
We introduce Free3D, a simple accurate method for monocular open-set novel view synthesis (NVS). Similar to Zero-1-to-3, we start from a pre-trained 2D image generator for generalization, and fine-tune it for NVS. Compared to other works…
Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability…
Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single input image, or by…
Novel view synthesis (NVS) from a single image is highly ill-posed due to large unobserved regions, especially for views that deviate significantly from the input. While existing methods focus on consistency between the source and generated…
Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent…
We introduce a novel method for dynamic free-view synthesis of an ambient scenes from a monocular capture bringing a immersive quality to the viewing experience. Our method builds upon the recent advancements in 3D Gaussian Splatting (3DGS)…
We present Stable View Synthesis (SVS). Given a set of source images depicting a scene from freely distributed viewpoints, SVS synthesizes new views of the scene. The method operates on a geometric scaffold computed via…
Comprehensive testing of autonomous systems through simulation is essential to ensure the safety of autonomous driving vehicles. This requires the generation of safety-critical scenarios that extend beyond the limitations of real-world data…
This paper considers the problem of generative novel view synthesis (GNVS), generating novel, plausible views of a scene given a limited number of known views. Here, we propose a set-based generative model that can simultaneously generate…
Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view…
Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. Bridging generation and novel view…
A free-viewpoint, editable, and high-fidelity driving simulator is crucial for training and evaluating end-to-end autonomous driving systems. In this paper, we present GA-Drive, a novel simulation framework capable of generating camera…