Saved in:
Bibliographic Details
Main Authors: Singh, Bharat, Kulharia, Viveka, Yang, Luyu, Ravichandran, Avinash, Tyagi, Ambrish, Shrivastava, Ashish
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.10722
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916288763265024
author Singh, Bharat
Kulharia, Viveka
Yang, Luyu
Ravichandran, Avinash
Tyagi, Ambrish
Shrivastava, Ashish
author_facet Singh, Bharat
Kulharia, Viveka
Yang, Luyu
Ravichandran, Avinash
Tyagi, Ambrish
Shrivastava, Ashish
contents Multimodal synthetic data generation is crucial in domains such as autonomous driving, robotics, augmented/virtual reality, and retail. We propose a novel approach, GenMM, for jointly editing RGB videos and LiDAR scans by inserting temporally and geometrically consistent 3D objects. Our method uses a reference image and 3D bounding boxes to seamlessly insert and blend new objects into target videos. We inpaint the 2D Regions of Interest (consistent with 3D boxes) using a diffusion-based video inpainting model. We then compute semantic boundaries of the object and estimate it's surface depth using state-of-the-art semantic segmentation and monocular depth estimation techniques. Subsequently, we employ a geometry-based optimization algorithm to recover the 3D shape of the object's surface, ensuring it fits precisely within the 3D bounding box. Finally, LiDAR rays intersecting with the new object surface are updated to reflect consistent depths with its geometry. Our experiments demonstrate the effectiveness of GenMM in inserting various 3D objects across video and LiDAR modalities.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10722
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR
Singh, Bharat
Kulharia, Viveka
Yang, Luyu
Ravichandran, Avinash
Tyagi, Ambrish
Shrivastava, Ashish
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimodal synthetic data generation is crucial in domains such as autonomous driving, robotics, augmented/virtual reality, and retail. We propose a novel approach, GenMM, for jointly editing RGB videos and LiDAR scans by inserting temporally and geometrically consistent 3D objects. Our method uses a reference image and 3D bounding boxes to seamlessly insert and blend new objects into target videos. We inpaint the 2D Regions of Interest (consistent with 3D boxes) using a diffusion-based video inpainting model. We then compute semantic boundaries of the object and estimate it's surface depth using state-of-the-art semantic segmentation and monocular depth estimation techniques. Subsequently, we employ a geometry-based optimization algorithm to recover the 3D shape of the object's surface, ensuring it fits precisely within the 3D bounding box. Finally, LiDAR rays intersecting with the new object surface are updated to reflect consistent depths with its geometry. Our experiments demonstrate the effectiveness of GenMM in inserting various 3D objects across video and LiDAR modalities.
title GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2406.10722