Related papers: Rein3D: Reinforced 3D Indoor Scene Generation with…
3D scene generation has quickly become a challenging new research direction, fueled by consistent improvements of 2D generative diffusion models. Most prior work in this area generates scenes by iteratively stitching newly generated frames…
Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However, these models still struggle with efficiently and explicitly…
Multi-view image generation holds significant application value in computer vision, particularly in domains like 3D reconstruction, virtual reality, and augmented reality. Most existing methods, which rely on extending single images, face…
Automatically generating a complete 3D scene from a text description, a reference image, or both has significant applications in fields like virtual reality and gaming. However, current methods often generate low-quality textures and…
We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered,…
3D scene reconstruction is a long-standing vision task. Existing approaches can be categorized into geometry-based and learning-based methods. The former leverages multi-view geometry but can face catastrophic failures due to the reliance…
Directly generating scenes from satellite imagery offers exciting possibilities for integration into applications like games and map services. However, challenges arise from significant view changes and scene scale. Previous efforts mainly…
Sparse RGBD scene completion is a challenging task especially when considering consistent textures and geometries throughout the entire scene. Different from existing solutions that rely on human-designed text prompts or predefined camera…
Dense 3D reconstruction and ego-motion estimation are key challenges in autonomous driving and robotics. Compared to the complex, multi-modal systems deployed today, multi-camera systems provide a simpler, low-cost alternative. However,…
Scene reconstruction and novel-view synthesis for large, complex, multi-story, indoor scenes is a challenging and time-consuming task. Prior methods have utilized drones for data capture and radiance fields for scene reconstruction, both of…
Generating realistic 3D objects from single-view images requires natural appearance, 3D consistency, and the ability to capture multiple plausible interpretations of unseen regions. Existing approaches often rely on fine-tuning pretrained…
Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis. However, accurately representing surfaces, especially in large and complex scenarios,…
Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation. Existing neural rendering approaches (e.g., NeRF, 3DGS) have achieved realistic reconstructions on large scenes, but optimize per…
Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric…
Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…
A single-pass driving clip frequently results in incomplete scanning of the road structure, making reconstructed scene expanding a critical requirement for sensor simulators to effectively regress driving actions. Although contemporary 3D…
Reconstructing dynamic 3D scenes from sparse multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating artifacts. Recent attempts introduce generative priors to hallucinate missing content,…
Empowering 3D Gaussian Splatting with generalization ability is appealing. However, existing generalizable 3D Gaussian Splatting methods are largely confined to narrow-range interpolation between stereo images due to their heavy backbones,…
State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control required to align generated content with specific scene requirements. Furthermore, without an underlying explicit geometry, these…
Real-time reconstruction of deformable surgical scenes is vital for advancing robotic surgery, improving surgeon guidance, and enabling automation. Recent methods achieve dense reconstructions from da Vinci robotic surgery videos, with…