Related papers: View-Consistent 3D Scene Editing via Dual-Path Str…

In this paper, we tackle a new task of 3D object synthesis, where a 3D model is composited with another object category to create a novel 3D model. However, most existing text/image/3D-to-3D methods struggle to effectively integrate…

Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

Text-driven image synthesis has made significant advancements with the development of diffusion models, transforming how visual content is generated from text prompts. Despite these advances, text-driven image editing, a key area in…

2D image representations are in regular grids and can be processed efficiently, whereas 3D point clouds are unordered and scattered in 3D space. The information inside these two visual domains is well complementary, e.g., 2D images have…

We present TRACE, a mesh-guided 3DGS editing framework that achieves automated, high-fidelity scene transformation. By anchoring video diffusion with explicit 3D geometry, TRACE uniquely enables fine-grained, part-level manipulatio--such as…

As 3D generation techniques continue to flourish, the demand for generating personalized content is rapidly rising. Users increasingly seek to apply various editing methods to polish generated 3D content, aiming to enhance its color, style,…

Multi-view image generation in autonomous driving demands consistent 3D scene understanding across camera views. Most existing methods treat this problem as a 2D image set generation task, lacking explicit 3D modeling. However, we argue…

Change detection plays a vital role in scene monitoring, exploration, and continual reconstruction. Existing 3D change detection methods often exhibit spatial inconsistency in the detected changes and fail to explicitly separate pre- and…

Recent advances in 4D Gaussian Splatting (4DGS) editing still face challenges with view, temporal, and non-editing region consistency, as well as with handling complex text instructions. To address these issues, we propose 4DGS-Craft, a…

A comprehensive semantic understanding of a scene is important for many applications - but in what space should diverse semantic information (e.g., objects, scene categories, material types, texture, etc.) be grounded and what should be its…

Numerous diffusion models have recently been applied to image synthesis and editing. However, editing 3D scenes is still in its early stages. It poses various challenges, such as the requirement to design specific methods for different…

We present SPAD, a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view generation, we repurpose a pretrained 2D diffusion model by extending its self-attention layers with…

3D content creation via text-driven stylization has played a fundamental challenge to multimedia and graphics community. Recent advances of cross-modal foundation models (e.g., CLIP) have made this problem feasible. Those approaches…

With the increasing popularity of autonomous driving based on the powerful and unified bird's-eye-view (BEV) representation, a demand for high-quality and large-scale multi-view video data with accurate annotation is urgently required.…

Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality.…

Real-time scene parsing is a fundamental feature for autonomous driving vehicles with multiple cameras. In this letter we demonstrate that sharing semantics between cameras with different perspectives and overlapped views can boost the…

We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes. The proposed method does not necessitate 3D…

We present Style3D, a novel approach for generating stylized 3D objects from a content image and a style image. Unlike most previous methods that require case- or style-specific training, Style3D supports instant 3D object stylization. Our…

With the rapid advancement of intelligent transportation systems, text-driven image generation and editing techniques have demonstrated significant potential in providing rich, controllable visual scene data for applications such as traffic…