Related papers: Cycle-Consistent Generative Rendering for 2D-3D Mo…

This paper presents a method to reconstruct high-quality textured 3D models from both multi-view and single-view images. The reconstruction is posed as an adaptation problem and is done progressively where in the first stage, we focus on…

3D-aware image synthesis aims at learning a generative model that can render photo-realistic 2D images while capturing decent underlying 3D shapes. A popular solution is to adopt the generative adversarial network (GAN) and replace the…

We propose an approach to 3D reconstruction via inverse procedural modeling and investigate two variants of this approach. The first option consists in the fitting set of input parameters using a genetic algorithm. We demonstrate the…

We train generative 'up-convolutional' neural networks which are able to generate images of objects given object style, viewpoint, and color. We train the networks on rendered 3D models of chairs, tables, and cars. Our experiments show that…

Learning 3D representations that generalize well to arbitrarily oriented inputs is a challenge of practical importance in applications varying from computer vision to physics and chemistry. We propose a novel multi-resolution convolutional…

Continual learning has been extensively studied for classification tasks with methods developed to primarily avoid catastrophic forgetting, a phenomenon where earlier learned concepts are forgotten at the expense of more recent samples. In…

In recent years, substantial progress has been achieved in learning-based reconstruction of 3D objects. At the same time, generative models were proposed that can generate highly realistic images. However, despite this success in these…

Recent years have seen remarkable progress in deep learning powered visual content creation. This includes deep generative 3D-aware image synthesis, which produces high-idelity images in a 3D-consistent manner while simultaneously capturing…

In recent years, deep generative models have gained significance due to their ability to synthesize natural-looking images with applications ranging from virtual reality to data augmentation for training computer vision models. While…

We study the problem of 3D object generation. We propose a novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional…

Self-supervised learning has emerged as a promising approach for acquiring transferable 3D representations from unlabeled 3D point clouds. Unlike 2D images, which are widely accessible, acquiring 3D assets requires specialized expertise or…

Diffusion models have shown great promise for image generation, beating GANs in terms of generation diversity, with comparable image quality. However, their application to 3D shapes has been limited to point or voxel representations that…

Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain complex phenomena such as thin structures, evolving topology, translucency, scattering, occlusion, and biological motion. Mesh-based reconstruction and…

This paper presents Omni-View, which extends the unified multimodal understanding and generation to 3D scenes based on multiview images, exploring the principle that "generation facilitates understanding". Consisting of understanding model,…

We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our model samples from the distribution of possible renderings consistent with the input and, even in the presence of…

This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision. In the viewer-centered coordinates, we construct an end-to-end trainable conditional variational framework to…

Differentiable rendering is a technique to connect 3D scenes with corresponding 2D images. Since it is differentiable, processes during image formation can be learned. Previous approaches to differentiable rendering focus on mesh-based…

This paper presents a novel decoder-based approach for generating manufacturable 3D structures optimized for additive manufacturing. We introduce a deep learning framework that decodes latent representations into geometrically valid,…

The generation of smooth and continuous images between domains has recently drawn much attention in image-to-image (I2I) translation. Linear relationship acts as the basic assumption in most existing approaches, while applied to different…

Human perception of 3D shapes goes beyond reconstructing them as a set of points or a composition of geometric primitives: we also effortlessly understand higher-level shape structure such as the repetition and reflective symmetry of object…