Rescan: Inductive Instance Segmentation for Indoor RGBD Scans

Halber, Maciej; Shi, Yifei; Xu, Kai

doi:10.1109/iccv.2019.00263

Cited by 12 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Change detection from scenes captured from different moments has been studied in various research fields. [16,2,13] discussed change detection from indoor scenes. There are also existing studies which discuss change detection for disaster management [30,12], resource monitoring [21,29], and vehicle navigation [1].…”

Section: Change Detectionmentioning

confidence: 99%

“…There are also existing studies which discuss change detection for disaster management [30,12], resource monitoring [21,29], and vehicle navigation [1]. Among existing change detection studies, [16,2,13] proposed rule-based methods for detecting changed parts from a set of 3-D maps. [21,29,1,30,12] discuss generating pixel-level maps for indicating the changed region between image pairs.…”

Section: Change Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Describing and Localizing Multiple Changes with Transformers

Qiu

Yamamoto

Nakashima

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Change captioning tasks aim to detect changes in image pairs observed before and after a scene change and generate a natural language description of the changes. Existing change captioning studies have mainly focused on scenes with a single change. However, detecting and describing multiple changed parts in image pairs is essential for enhancing adaptability to complex scenarios. We solve the above issues from three aspects: (i) We propose a CG-based multi-change captioning dataset; (ii) We benchmark existing state-of-the-art methods of single change captioning on multi-change captioning; (iii) We further propose Multi-Change Captioning transformers (MCCFormers) that identify change regions by densely correlating different regions in image pairs and dynamically determines the related change regions with words in sentences. The proposed method obtained the highest scores on four conventional change captioning evaluation metrics for multichange captioning. In addition, existing methods generate a single attention map for multiple changes and lack the ability to distinguish change regions. In contrast, our proposed method can separate attention maps for each change and performs well with respect to change localization. Moreover, the proposed framework outperformed the previous state-of-the-art methods on an existing change captioning benchmark, CLEVR-Change, by a large margin (+6.1 on BLEU-4 and +9.7 on CIDEr scores), indicating its general ability in change captioning tasks. Our code and dataset will be publicly available through the project page 1 . Before Change captions After Caption 1: The large gray rubber sphere has disappeared. (delete) Caption 2: There is no longer a large cyan metal cube. (delete) Caption 3: The large brown metal sphere was moved from its original location. (move) Caption 4: The small yellow rubber cylinder was replaced by a small red rubber sphere. (replace)

show abstract

Section: Change Detectionmentioning

confidence: 99%

Section: Change Detectionmentioning

confidence: 99%

Describing and Localizing Multiple Changes with Transformers

Qiu

Yamamoto

Nakashima

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…Existing reconstructions of indoor spaces are limited in scale. Common reconstruction datasets consist primarily of scans for regions of rooms and single rooms [1,2,[15][16][17]. 1 There exist datasets with building level reconstruction, but these are limited in the overall number of scenes and real-world spaces (BuildingParser [18], 2D-3D-S [3], Matterport3D [4]).…”

Section: Related Workmentioning

confidence: 99%

Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI

Ramakrishnan¹,

Gokaslan²,

Wijmans³

et al. 2021

Preprint

View full text Add to dashboard Cite

Figure 1: The Habitat-Matterport 3D (HM3D) dataset of large-scale 3D and photorealistic environments provides 1,000 building-scale reconstructions of interiors from a diverse set of geographic locations. The scale, completeness, and visual fidelity of these reconstructions surpass those of prior datasets, and enable research on embodied AI agents that can perceive, navigate, and act within realistic indoor environments. The image on the left displays a collage of a subset of HM3D scans. The image on the top-right is a close-up view of a specific scan, and the images on the bottom-right are snapshots from two camera viewpoints in the scan.

show abstract

“…While some works [50,57] advocates continuous temporal-dynamics modeling, we instead assume discrete non-sequential input and enforce consistency using synchronization, hence are more applicable in real-world. Similarly, [27,68] propose to perform instance level re-localization in a changed scene. Nevertheless, we do not assume a pre-segmentation of the scene, but instead performs joint motion segmentation.…”

Section: Related Workmentioning

confidence: 99%

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

Huang

Wang

Birdal

et al. 2021

Preprint

View full text Add to dashboard Cite

We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial challenges posed by this multi-scan multibody setting that we investigate are: (i) guaranteeing correspondence and segmentation consistency across multiple input point clouds capturing different spatial arrangements of bodies or body parts; and (ii) obtaining robust motionbased rigid body segmentation applicable to novel object categories.We propose an approach to address these issues that incorporates spectral synchronization into an iterative deep declarative network, so as to simultaneously recover consistent correspondences as well as motion segmentation. At the same time, by explicitly disentangling the correspondence and motion segmentation estimation modules, we achieve strong generalizability across different object categories. Our extensive evaluations demonstrate that our method is effective on various datasets ranging from rigid parts in articulated objects to individually moving objects in a 3D scene, be it single-view or full point clouds. Code at https://github.com/ huangjh-pub/multibody-sync.

show abstract

Rescan: Inductive Instance Segmentation for Indoor RGBD Scans

Cited by 12 publications

References 45 publications

Describing and Localizing Multiple Changes with Transformers

Describing and Localizing Multiple Changes with Transformers

Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

Contact Info

Product

Resources

About