Related papers: Ouroboros3D: Image-to-3D Generation via 3D-aware R…
Diffusion models, known for their powerful generative capabilities, play a crucial role in addressing real-world super-resolution challenges. However, these models often focus on improving local textures while neglecting the impacts of…
Encouraged by the growing availability of pre-trained 2D diffusion models, image-to-3D generation by leveraging Score Distillation Sampling (SDS) is making remarkable progress. Most existing methods combine novel-view lifting from 2D…
Establishing reliable correspondences is crucial for all registration tasks, including 2D image registration, 3D point cloud registration, and 2D-3D image-to-point cloud registration. However, these tasks are often complicated by challenges…
Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurately modeling driving scenes and generating long videos. To…
Score distillation sampling~(SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a \textbf{single} image. It leverages pre-trained 2D diffusion models as teacher to guide the reconstruction…
Object manipulation in images aims to not only edit the object's presentation but also gift objects with motion. Previous methods encountered challenges in concurrently handling static editing and dynamic generation, while also struggling…
Automatically generating multiview illusions is a compelling challenge, where a single piece of visual content offers distinct interpretations from different viewing perspectives. Traditional methods, such as shadow art and wire art, create…
Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained…
Current image-to-3D approaches suffer from high computational costs and lack scalability for high-resolution outputs. In contrast, we introduce a novel framework to directly generate explicit surface geometry and texture using multi-view 2D…
Multiview diffusion models have rapidly emerged as a powerful tool for content creation with spatial consistency across viewpoints, offering rich visual realism without requiring explicit geometry and appearance representation. However,…
Advancements in text-to-image diffusion models have led to significant progress in fast 3D content creation. One common approach is to generate a set of multi-view images of an object, and then reconstruct it into a 3D model. However, this…
We present Farm3D, a method for learning category-specific 3D reconstructors for articulated objects, relying solely on "free" virtual supervision from a pre-trained 2D diffusion-based image generator. Recent approaches can learn a…
Diffusion models have achieved great success in generating 2D images. However, the quality and generalizability of 3D content generation remain limited. State-of-the-art methods often require large-scale 3D assets for training, which are…
Given a single image of a target object, image-to-3D generation aims to reconstruct its texture and geometric shape. Recent methods often utilize intermediate media, such as multi-view images or videos, to bridge the gap between input image…
As a promising 3D generation technique, multiview diffusion (MVD) has received a lot of attention due to its advantages in terms of generalizability, quality, and efficiency. By finetuning pretrained large image diffusion models with 3D…
Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. Inspired by concepts from the renormalization group in physics, which analyzes systems across different scales, we…
3D structure modeling is essential across scales, enabling applications from fluid simulation and 3D reconstruction to protein folding and molecular docking. Yet, despite shared 3D spatial patterns, current approaches remain fragmented,…
We present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks in a unified framework. DiffBIR decouples blind image restoration problem into two stages: 1) degradation removal: removing…
Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas…
High-fidelity spectrum cartography is pivotal for spectrum management and wireless situational awareness, yet it remains a challenging ill-posed inverse problem due to the sparsity and irregularity of observations. Furthermore, existing…