Related papers: Input-level Inductive Biases for 3D Reconstruction

Embedding of large but redundant data, such as images or text, in a hierarchy of lower-dimensional spaces is one of the key features of representation learning approaches, which nowadays provide state-of-the-art solutions to problems once…

Existing deep learning-based image inpainting methods typically rely on convolutional networks with RGB images to reconstruct images. However, relying exclusively on RGB images may neglect important depth information, which plays a critical…

Recent advances in leveraging large-scale Internet photo collections for 3D reconstruction have enabled immersive virtual exploration of landmarks and historic sites worldwide. However, little attention has been given to the immersive…

Reliable 3D reconstruction from in-the-wild image collections is often hindered by "noisy" images-irrelevant inputs with little or no view overlap with others. While traditional Structure-from-Motion pipelines handle such cases through…

Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are…

We propose a method for converting a single RGB-D input image into a 3D photo - a multi-layer representation for novel view synthesis that contains hallucinated color and depth structures in regions occluded in the original view. We use a…

Recently deep neutral networks have achieved promising performance for filling large missing regions in image inpainting tasks. They usually adopted the standard convolutional architecture over the corrupted image, leading to meaningless…

We present an architecture which lets us train deep, directed generative models with many layers of latent variables. We include deterministic paths between all latent variables and the generated output, and provide a richer set of…

Recovering the 3D shape of transparent objects using a small number of unconstrained natural images is an ill-posed problem. Complex light paths induced by refraction and reflection have prevented both traditional and deep multiview stereo…

3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronged approach to address these issues. To better incorporate…

Modeling scene geometry using implicit neural representation has revealed its advantages in accuracy, flexibility, and low memory usage. Previous approaches have demonstrated impressive results using color or depth images but still have…

Exploiting internal spatial geometric constraints of sparse LiDARs is beneficial to depth completion, however, has been not explored well. This paper proposes an efficient method to learn geometry-aware embedding, which encodes the local…

This paper presents a method to reconstruct high-quality textured 3D models from single images. Current methods rely on datasets with expensive annotations; multi-view images and their camera parameters. Our method relies on GAN generated…

While deep Embedding Learning approaches have witnessed widespread success in multiple computer vision tasks, the state-of-the-art methods for representing natural images need not necessarily perform well on images from other domains, such…

Neural implicit representations have emerged as a powerful paradigm for 3D reconstruction. However, despite their success, existing methods fail to capture fine geometric details and thin structures, especially in scenarios where only…

Monocular 3D face reconstruction plays a crucial role in avatar generation, with significant demand in web-related applications such as generating virtual financial advisors in FinTech. Current reconstruction methods predominantly rely on…

Current 3D GAN inversion methods for human heads typically use only one single frontal image to reconstruct the whole 3D head model. This leaves out meaningful information when multi-view data or dynamic videos are available. Our method…

The open vocabulary capability of 3D models is increasingly valued, as traditional methods with models trained with fixed categories fail to recognize unseen objects in complex dynamic 3D scenes. In this paper, we propose a simple yet…

We show that generative models can be used to capture visual geometry constraints statistically. We use this fact to infer the 3D shape of object categories from raw single-view images. Differently from prior work, we use no external…

Transformer-based end-to-end speech recognition has achieved great success. However, the large footprint and computational overhead make it difficult to deploy these models in some real-world applications. Model compression techniques can…