Related papers: MVGenMaster: Scaling Multi-View Generation from An…

Text-driven 3D editing enables user-friendly 3D object or scene editing with text instructions. Due to the lack of multi-view consistency priors, existing methods typically resort to employing 2D generation or editing models to process each…

Diffusion-based approaches have recently demonstrated strong performance for single-image novel view synthesis by conditioning generative models on geometry inferred from monocular depth estimation. However, in practice, the quality and…

A unified diffusion framework for multi-modal generation and understanding has the transformative potential to achieve seamless and controllable image diffusion and other cross-modal tasks. In this paper, we introduce MMGen, a unified…

We introduce GarmentCrafter, a new approach that enables non-professional users to create and modify 3D garments from a single-view image. While recent advances in image generation have facilitated 2D garment design, creating and editing 3D…

Generating high-quality novel views of a scene from a single image requires maintaining structural coherence across different views, referred to as view consistency. While diffusion models have driven advancements in novel view synthesis,…

We present Viewset Diffusion, a diffusion-based generator that outputs 3D objects while only using multi-view 2D data for supervision. We note that there exists a one-to-one mapping between viewsets, i.e., collections of several 2D views of…

Recent advances in generative diffusion models have enabled the previously unfeasible capability of generating 3D assets from a single input image or a text prompt. In this work, we aim to enhance the quality and functionality of these…

We propose a novel approach for 3D shape completion by synthesizing multi-view depth maps. While previous work for shape completion relies on volumetric representations, meshes, or point clouds, we propose to use multi-view depth maps from…

We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges…

3D human reconstruction from a single image is a challenging problem and has been exclusively studied in the literature. Recently, some methods have resorted to diffusion models for guidance, optimizing a 3D representation via Score…

Multi-view inverse rendering aims to recover geometry, materials, and illumination consistently across multiple viewpoints. When applied to multi-view images, existing single-view approaches often ignore cross-view relationships, leading to…

Multiview diffusion models have shown considerable success in image-to-3D generation for general objects. However, when applied to human data, existing methods have yet to deliver promising results, largely due to the challenges of scaling…

We introduce EscherNet, a multi-view conditioned diffusion model for view synthesis. EscherNet learns implicit and generative 3D representations coupled with a specialised camera positional encoding, allowing precise and continuous relative…

In this work, we propose a novel approach to prioritize the depth map computation of multi-view stereo (MVS) to obtain compact 3D point clouds of high quality and completeness at low computational cost. Our prioritization approach operates…

In this work, we introduce Unique3D, a novel image-to-3D framework for efficiently generating high-quality 3D meshes from single-view images, featuring state-of-the-art generation fidelity and strong generalizability. Previous methods based…

The creation of 3D human face avatars from a single unconstrained image is a fundamental task that underlies numerous real-world vision and graphics applications. Despite the significant progress made in generative models, existing methods…

Human head detection, keypoint estimation, and 3D head model fitting are essential tasks with many applications. However, traditional real-world datasets often suffer from bias, privacy, and ethical concerns, and they have been recorded in…

Text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models has shown great promise but still suffers from inconsistent 3D geometric structures (Janus problems) and severe artifacts. The aforementioned problems…

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…

While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require…