An official website of the United States government
Finding correspondences is a fundamental and extensively researched problem in computer vision and graphics. In this work, we examine the underexplored problem of estimating segmentation-to-segmentation correspondence between images in the wild and untextured 3D shapes. This task is highly challenging due to substantial differences in appearance, geometry, and viewpoint. Our approach bridges the cross-modality gap by linking pixels in the image segment to vertices in the corresponding semantic part of the 3D shape. To achieve this, we first distill deep visual features from a 2D vision model onto the 3D shape surface, allowing for the computation of feature similarity between image pixels and shape vertices. We then identify Best Segmentation Buddies, vertices whose most similar image pixel lies within the image segmentation region, enabling the reliable discovery of vertices in semantically corresponding shape parts. Finally, we leverage distilled 3D features from the 2D image segmentation model to segment the shape directly in 3D, bootstrapping the correspondence process. We demonstrate the generality and robustness of our approach across a wide range of image-shape pairs, showcasing accurate and semantically meaningful correspondences.
more »
« less
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
- 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 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
-
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
-
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
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- https://doi.org/10.1145/3680528.3687605
