Related papers: Unaligned 2D to 3D Translation with Conditional Ve…

We address the problem of generating images across two drastically different views, namely ground (street) and aerial (overhead) views. Image synthesis by itself is a very challenging computer vision task and is even more so when generation…

Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors. Recently, the integration of Neural Radiance Fields (NeRFs) and…

Spatial control methods using additional modules on pretrained diffusion models have gained attention for enabling conditional generation in natural images. These methods guide the generation process with new conditions while leveraging the…

Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new…

Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results. Furthermore,…

This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view…

We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models. While existing diffusion-based methods operate on images, latent codes, or point cloud data, we are the first to…

Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as…

Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time limits the deployment in real scenarios. This work aims at…

Realistic color texture generation is an important step in RGB-D surface reconstruction, but remains challenging in practice due to inaccuracies in reconstructed geometry, misaligned camera poses, and view-dependent imaging artifacts. In…

Recent remarkable advances in large-scale text-to-image diffusion models have inspired a significant breakthrough in text-to-3D generation, pursuing 3D content creation solely from a given text prompt. However, existing text-to-3D…

Inferring 3D structures from sparse, unposed observations is challenging due to its unconstrained nature. Recent methods propose to predict implicit representations directly from unposed inputs in a data-driven manner, achieving promising…

Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is critical for downstream…

Novel view synthesis is a fundamental challenge in image-to-3D generation, requiring the generation of target view images from a set of conditioning images and their relative poses. While recent approaches like Zero-1-to-3 have demonstrated…

We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. To perform novel view synthesis in this under-constrained setting, we capitalize on the geometric priors that large-scale…

Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. In this work, we propose \textbf{ViewCrafter}, a novel method for synthesizing high-fidelity novel…

We present a data-driven method for learning to generate animations of 3D garments using a 2D image diffusion model. In contrast to existing methods, typically based on fully connected networks, graph neural networks, or generative…

We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-tuning an image generator, pre-trained on billions of real…

In multimodal unsupervised image-to-image translation tasks, the goal is to translate an image from the source domain to many images in the target domain. We present a simple method that produces higher quality images than current…

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…