Related papers: Pixel-Aligned Multi-View Generation with Depth Gui…

Diffusion models have impressive image generation capability, but low-quality generations still exist, and their identification remains challenging due to the lack of a proper sample-wise metric. To address this, we propose BayesDiff, a…

Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging. Previous methods typically invert a target image back to the latent space either by…

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…

Diffusion models are highly regarded for their controllability and the diversity of images they generate. However, class-conditional generation methods based on diffusion models often focus on more common categories. In large-scale…

Despite recent successes in synthesizing faces and bedrooms, existing generative models struggle to capture more complex image types, potentially due to the oversimplification of their latent space constructions. To tackle this issue,…

Multi-view diffusion models have shown promise in 3D novel view synthesis, but most existing methods adopt a non-autoregressive formulation. This limits their applicability in world modeling, as they only support a fixed number of views and…

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods…

Taking advantage of the many recent advances in deep learning, text-to-image generative models currently have the merit of attracting the general public attention. Two of these models, DALL-E 2 and Imagen, have demonstrated that highly…

We introduce Reangle-A-Video, a unified framework for generating synchronized multi-view videos from a single input video. Unlike mainstream approaches that train multi-view video diffusion models on large-scale 4D datasets, our method…

Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D generation tends to produce results with inconsistent appearances (e.g., faces on the back view) and inaccurate shapes (e.g., animals with extra…

While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a significant challenge due to the complexities of multi-view consistency and spatial control.…

We introduce a unified single and multi-view neural implicit 3D reconstruction framework VPFusion. VPFusion attains high-quality reconstruction using both - 3D feature volume to capture 3D-structure-aware context, and pixel-aligned image…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

While objects from different categories can be reliably decoded from fMRI brain response patterns, it has proved more difficult to distinguish visually similar inputs, such as different instances of the same category. Here, we apply a…

Text-guided diffusion models have shown superior performance in image/video generation and editing. While few explorations have been performed in 3D scenarios. In this paper, we discuss three fundamental and interesting problems on this…

Most multi-view 3D reconstruction algorithms, especially when shape-from-shading cues are used, assume that object appearance is predominantly diffuse. To alleviate this restriction, we introduce S2Dnet, a generative adversarial network for…

We present a novel framework for high-fidelity novel view synthesis (NVS) from sparse images, addressing key limitations in recent feed-forward 3D Gaussian Splatting (3DGS) methods built on Vision Transformer (ViT) backbones. While…

This paper addresses a challenging problem -- how to generate multi-view cloth images from only a single view input. To generate realistic-looking images with different views from the input, we propose a new image generation model termed…

Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on…