Related papers: Structurally Disentangled Feature Fields Distillat…

Confounding bias is a crucial problem when applying machine learning to practice, especially in clinical practice. We consider the problem of learning representations independent to multiple biases. In literature, this is mostly solved by…

We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both…

We introduce Structured 3D Features, a model based on a novel implicit 3D representation that pools pixel-aligned image features onto dense 3D points sampled from a parametric, statistical human mesh surface. The 3D points have associated…

Learning dexterous manipulation from few-shot demonstrations is a significant yet challenging problem for advanced, human-like robotic systems. Dense distilled feature fields have addressed this challenge by distilling rich semantic…

Grounding natural language to the physical world is a ubiquitous topic with a wide range of applications in computer vision and robotics. Recently, 2D vision-language models such as CLIP have been widely popularized, due to their impressive…

We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects…

In this paper we introduce a new approach to computing hidden features of sampled vector fields. The basic idea is to convert the vector field data to a graph structure and use tools designed for automatic, unsupervised analysis of graphs.…

We propose PartField, a feedforward approach for learning part-based 3D features, which captures the general concept of parts and their hierarchy without relying on predefined templates or text-based names, and can be applied to open-world…

Taking an image of an object is at its core a lossy process. The rich information about the three-dimensional structure of the world is flattened to an image plane and decisions such as viewpoint and camera parameters are final and not…

Domain adaptation aims to mitigate the domain gap when transferring knowledge from an existing labeled domain to a new domain. However, existing disentanglement-based methods do not fully consider separation between domain-invariant and…

Indoor scene semantic parsing from RGB images is very challenging due to occlusions, object distortion, and viewpoint variations. Going beyond prior works that leverage geometry information, typically paired depth maps, we present a new…

The success of supervised learning requires large-scale ground truth labels which are very expensive, time-consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike…

Monocular 3D Object Detection represents a challenging Computer Vision task due to the nature of the input used, which is a single 2D image, lacking in any depth cues and placing the depth estimation problem as an ill-posed one. Existing…

Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. Due to the scarcity of 3D data, state-of-the-art approaches utilize pre-trained 2D diffusion priors, optimized…

Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs which use neural 3D volumetric representations for synthesis.…

In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed…

There have been a fairly of research interests in exploring the disentanglement of appearance and shape from human images. Most existing endeavours pursuit this goal by either using training images with annotations or regulating the…

Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly…

While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches…

Transferring the style from one image onto another is a popular and widely studied task in computer vision. Yet, style transfer in the 3D setting remains a largely unexplored problem. To our knowledge, we propose the first learning-based…