Related papers: WeatherEdit: Controllable Weather Editing with 4D …

Controllable driving scene generation is critical for realistic and scalable autonomous driving simulation, yet existing approaches struggle to jointly achieve photorealism and precise control. We introduce HorizonForge, a unified framework…

With the emergence of large-scale Text-to-Image(T2I) models and implicit 3D representations like Neural Radiance Fields (NeRF), many text-driven generative editing methods based on NeRF have appeared. However, the implicit encoding of…

We present DrivingGaussian++, an efficient and effective framework for realistic reconstructing and controllable editing of surrounding dynamic autonomous driving scenes. DrivingGaussian++ models the static background using incremental 3D…

Many 3D scene editing tasks focus on modifying local regions rather than the entire scene, except for some global applications like style transfer, and in the context of 3D Gaussian Splatting (3DGS), where scenes are represented by a series…

In this work, we propose a novel approach, namely WeatherDG, that can generate realistic, weather-diverse, and driving-screen images based on the cooperation of two foundation models, i.e, Stable Diffusion (SD) and Large Language Model…

We present a novel framework for generating photorealistic 3D human head and subsequently manipulating and reposing them with remarkable flexibility. The proposed approach leverages an implicit function representation of 3D human heads,…

We consider the problem of adding dynamic rain effects to in-the-wild scenes in a physically-correct manner. Recent advances in scene modeling have made significant progress, with NeRF and 3DGS techniques emerging as powerful tools for…

Driving scene manipulation with sensor data is emerging as a promising alternative to traditional virtual driving simulators. However, existing frameworks struggle to generate realistic scenarios efficiently due to limited editing…

We present BlenderFusion, a generative visual compositing framework that synthesizes new scenes by recomposing objects, camera, and background. It follows a layering-editing-compositing pipeline: (i) segmenting and converting visual inputs…

We propose a method for authoring non-realistic 3D objects (represented as either 3D Gaussian Splats or meshes), that comply with 2D edits from specific viewpoints. Namely, given a 3D object, a user chooses different viewpoints and…

We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model…

The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D…

Scene representations using 3D Gaussian primitives have produced excellent results in modeling the appearance of static and dynamic 3D scenes. Many graphics applications, however, demand the ability to manipulate both the appearance and the…

While AI-based numerical weather prediction (NWP) enables rapid forecasting, generating high-resolution outputs remains computationally demanding due to limited multi-scale adaptability and inefficient data representations. We propose the…

Adverse climate conditions pose significant challenges for autonomous systems, demanding reliable perception and decision-making across diverse environments. To better simulate these conditions, physically-based NeRF rendering methods have…

We present a novel framework for enhancing the visual fidelity and consistency of text-guided 3D Gaussian Splatting (3DGS) editing. Existing editing approaches face two critical challenges: inconsistent geometric reconstructions across…

Perception robustness under adverse weather remains a critical challenge for autonomous driving, with the core bottleneck being the scarcity of real-world video data in adverse weather. Existing weather generation approaches struggle to…

Recent 4D dynamic scene editing methods require editing thousands of 2D images used for dynamic scene synthesis and updating the entire scene with additional training loops, resulting in several hours of processing to edit a single dynamic…

Novel view synthesis with neural models has advanced rapidly in recent years, yet adapting these models to scene changes remains an open problem. Existing methods are either labor-intensive, requiring extensive model retraining, or fail to…

User-friendly 3D object editing is a challenging task that has attracted significant attention recently. The limitations of direct 3D object editing without 2D prior knowledge have prompted increased attention towards utilizing 2D…