Related papers: GOEmbed: Gradient Origin Embeddings for Representa…

Precisely perceiving the geometric and semantic properties of real-world 3D objects is crucial for the continued evolution of augmented reality and robotic applications. To this end, we present Foundation Model Embedded Gaussian Splatting…

We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs. The approach learns an encoding of the samples in the training…

State-of-the-art learning-based monocular 3D reconstruction methods learn priors over object categories on the training set, and as a result struggle to achieve reasonable generalization to object categories unseen during training. In this…

Generating high-quality 3D content from text, single images, or sparse view images remains a challenging task with broad applications. Existing methods typically employ multi-view diffusion models to synthesize multi-view images, followed…

Human perception for effective object tracking in 2D video streams arises from the implicit use of prior 3D knowledge and semantic reasoning. In contrast, most generic object tracking (GOT) methods primarily rely on 2D features of the…

Generating images via the generative adversarial network (GAN) has attracted much attention recently. However, most of the existing GAN-based methods can only produce low-resolution images of limited quality. Directly generating…

Vision-Language models like CLIP have been widely adopted for various tasks due to their impressive zero-shot capabilities. However, CLIP is not suitable for extracting 3D geometric features as it was trained on only images and text by…

Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined graph through a series of graph convolutions, leading to…

Vision-language foundation models such as CLIP have achieved tremendous results in global vision-language alignment, but still show some limitations in creating representations for specific image regions. % To address this problem, we…

Learning effective multi-modal 3D representations of objects is essential for numerous applications, such as augmented reality and robotics. Existing methods often rely on task-specific embeddings that are tailored either for semantic…

We tackle the task of synthesizing novel views of an object given a few input images and associated camera viewpoints. Our work is inspired by recent 'geometry-free' approaches where multi-view images are encoded as a (global) set-latent…

Recent techniques on implicit geometry representation learning and neural rendering have shown promising results for 3D clothed human reconstruction from sparse video inputs. However, it is still challenging to reconstruct detailed surface…

Recent research has shown that controllable image generation based on pre-trained GANs can benefit a wide range of computer vision tasks. However, less attention has been devoted to 3D vision tasks. In light of this, we propose a novel…

We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. The framework consists of two innovative fusion schemes. Firstly, unlike existing multimodal methods that necessitate…

We present a method to learn the 3D surface of objects directly from a collection of images. Previous work achieved this capability by exploiting additional manual annotation, such as object pose, 3D surface templates, temporal continuity…

Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep AutoEncoder (AE) network with…

We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple, effective, and robust geometric algorithm that can segment objects in 3D scenes without annotations or training on scenes. We achieve such unsupervised…

Object encoding and identification are vital for robotic tasks such as autonomous exploration, semantic scene understanding, and re-localization. Previous approaches have attempted to either track objects or generate descriptors for object…

Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appearance to 3D properties…

Global illumination (GI) is essential for realistic rendering but remains computationally expensive due to the complexity of simulating indirect light transport. Recent neural methods have mainly relied on per-scene optimization, sometimes…