An official website of the United States government
We present RealFusion, an interactive workflow that supports early stage design ideation in a digital 3D medium. RealFusion is inspired by the practice of found-object-art, wherein new representations are created by composing existing objects. The key motivation behind our approach is direct creation of 3D artifacts during design ideation, in contrast to conventional practice of employing 2D sketching. RealFusion comprises of three creative states where users can (a) repurpose physical objects as modeling components, (b) modify the components to explore different forms, and (c) compose them into a meaningful 3D model. We demonstrate RealFusion using a simple interface that comprises of a depth sensor and a smartphone. To achieve direct and efficient manipulation of modeling elements, we also utilize mid-air interactions with the smartphone. We conduct a user study with novice designers to evaluate the creative outcomes that can be achieved using RealFusion.
more »
« less
This content will become publicly available on December 3, 2025
iSeg: Interactive 3D Segmentation via Interactive Attention
We present iSeg, a new interactive technique for segmenting 3D shapes. Previous works have focused mainly on leveraging pre-trained 2D foundation models for 3D segmentation based on text. However, text may be insufficient for accurately describing fine-grained spatial segmentations. Moreover, achieving a consistent 3D segmentation using a 2D model is highly challenging, since occluded areas of the same semantic region may not be visible together from any 2D view. Thus, we design a segmentation method conditioned on fine user clicks, which operates entirely in 3D. Our system accepts user clicks directly on the shape's surface, indicating the inclusion or exclusion of regions from the desired shape partition. To accommodate various click settings, we propose a novel interactive attention module capable of processing different numbers and types of clicks, enabling the training of a single unified interactive segmentation model. We apply iSeg to a myriad of shapes from different domains, demonstrating its versatility and faithfulness to the user's specifications. Our project page is at https://threedle.github.io/iSeg/.
more »
« less
- Award ID(s):
- 2304481
- PAR ID:
- 10572459
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9798400711312
- Page Range / eLocation ID:
- 1 to 11
- Format(s):
- Medium: X
- Location:
- Tokyo Japan
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present a neural technique for learning to select a local sub-region around a point which can be used for mesh parameterization. The motivation for our framework is driven by interactive workflows used for decaling, texturing, or painting on surfaces. Our key idea is to incorporate segmentation probabilities as weights of a classical parameterization method, implemented as a novel differentiable parameterization layer within a neural network framework. We train a segmentation network to select 3D regions that are parameterized into 2D and penalized by the resulting distortion, giving rise to segmentations which are distortion-aware. Following training, a user can use our system to interactively select a point on the mesh and obtain a large, meaningful region around the selection which induces a low-distortion parameterization.more » « less
-
null (Ed.)In this paper, we introduce a practical system for interactive video object mask annotation, which can support multiple back-end methods. To demonstrate the generalization of our system, we introduce a novel approach for video object annotation. Our proposed system takes scribbles at a chosen key-frame from the end-users via a user-friendly interface and produces masks of corresponding objects at the key-frame via the Control-Point-based Scribbles-to-Mask (CPSM) module. The object masks at the key-frame are then propagated to other frames and refined through the Multi-Referenced Guided Segmentation (MRGS) module. Last but not least, the user can correct wrong segmentation at some frames, and the corrected mask is continuously propagated to other frames in the video via the MRGS to produce the object masks at all video frames.more » « less
-
Internet image collections containing photos captured by crowds of photographers show promise for enabling digital exploration of large‐scale tourist landmarks. However, prior works focus primarily on geometric reconstruction and visualization, neglecting the key role of language in providing a semantic interface for navigation and fine‐grained understanding. In more constrained 3D domains, recent methods have leveraged modern vision‐and‐language models as a strong prior of 2D visual semantics. While these models display an excellent understanding of broad visual semantics, they struggle with unconstrained photo collections depicting such tourist landmarks, as they lack expert knowledge of the architectural domain and fail to exploit the geometric consistency of images capturing multiple views of such scenes. In this work, we present a localization system that connects neural representations of scenes depicting large‐scale landmarks with text describing a semantic region within the scene, by harnessing the power of SOTA vision‐and‐language models with adaptations for understanding landmark scene semantics. To bolster such models with fine‐grained knowledge, we leverage large‐scale Internet data containing images of similar landmarks along with weakly‐related textual information. Our approach is built upon the premise that images physically grounded in space can provide a powerful supervision signal for localizing new concepts, whose semantics may be unlocked from Internet textual metadata with large language models. We use correspondences between views of scenes to bootstrap spatial understanding of these semantics, providing guidance for 3D‐compatible segmentation that ultimately lifts to a volumetric scene representation. To evaluate our method, we present a new benchmark dataset containing large‐scale scenes with ground‐truth segmentations for multiple semantic concepts. Our results show that HaLo‐NeRF can accurately localize a variety of semantic concepts related to architectural landmarks, surpassing the results of other 3D models as well as strong 2D segmentation baselines. Our code and data are publicly available at https://tau‐vailab.github.io/HaLo‐NeRF/more » « less
-
null (Ed.)Deep learning models have achieved state-of-the-art performance in semantic image segmentation, but the results provided by fully automatic algorithms are not always guaranteed satisfactory to users. Interactive segmentation offers a solution by accepting user annotations on selective areas of the images to refine the segmentation results. However, most existing models only focus on correcting the current image’s misclassified pixels, with no knowledge carried over to other images. In this work, we formulate interactive image segmentation as a continual learning problem and propose a framework to effectively learn from user annotations, aiming to improve the segmentation on both the current image and unseen images in future tasks while avoiding deteriorated performance on previously-seen images. It employs a probabilistic mask to control the neural network’s kernel activation and extract the most suitable features for segmenting images in each task. We also design a task-aware architecture to automatically infer the optimal kernel activation for initial segmentation and subsequent refinement. Interactions with users are guided through multi-source uncertainty estimation so that users can focus on the most important areas to minimize the overall manual annotation effort. Extensive experiments are performed on both medical and natural image datasets to illustrate the proposed framework’s effectiveness on basic segmentation performance, forward knowledge transfer, and backward knowledge transfer.more » « less
