Related papers: Poster: Reliable 3D Reconstruction for Ad-hoc Edge…
We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation process of DreamCraft3D, but replaces the time-consuming…
In this paper, we present a robust and efficient Structure from Motion pipeline for accurate 3D reconstruction under challenging environments by leveraging the camera pose information from a visual-inertial odometry. Specifically, we…
Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for…
The polyhedron projection for 360-degree video is becoming more and more popular since it can lead to much less geometry distortion compared with the equirectangular projection. However, in the polyhedron projection, we can observe very…
Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements. Still, monocular 3D HPE is a challenging problem due to the inherent depth…
Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a…
We introduce an approach that accurately reconstructs 3D human poses and detailed 3D full-body geometric models from single images in realtime. The key idea of our approach is a novel end-to-end multi-task deep learning framework that uses…
Real-time, high-quality, 3D scanning of large-scale scenes is key to mixed reality and robotic applications. However, scalability brings challenges of drift in pose estimation, introducing significant errors in the accumulated model.…
Stereo video generation has been gaining increasing attention with recent advancements in video diffusion models. However, most existing methods focus on generating 3D stereoscopic videos from monocular 2D videos. These approaches typically…
While large deep neural networks excel at general video analytics tasks, the significant demand on computing capacity makes them infeasible for real-time inference on resource-constrained end cam-eras. In this paper, we propose an…
Single-image-to-3D generative models can now produce high-quality geometry, yet conditioning on a single view inevitably introduces ambiguity about unseen regions. Multi-view conditioning can reduce this ambiguity, but existing methods…
In this paper, we present a comprehensive study and propose several novel techniques for implementing 3D convolutional blocks using 2D and/or 1D convolutions with only 4D and/or 3D tensors. Our motivation is that 3D convolutions with 5D…
Multi-View Stereo plays a pivotal role in civil engineering by facilitating 3D modeling, precise engineering surveying, quantitative analysis, as well as monitoring and maintenance. It serves as a valuable tool, offering high-precision and…
3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and severe overfitting, precluding the adoption of powerful 3D perception models. In this work, we…
Real-time holistic scene understanding would allow machines to interpret their surrounding in a much more detailed manner than is currently possible. While panoptic image segmentation methods have brought image segmentation closer to this…
Due to the imperfect person detection results and posture changes, temporal appearance misalignment is unavoidable in video-based person re-identification (ReID). In this case, 3D convolution may destroy the appearance representation of…
Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios. In this paper, we rethink that the redundancy in inversion-based…
Diffusion models have risen as a promising approach to data-driven planning, and have demonstrated impressive robotic control, reinforcement learning, and video planning performance. Given an effective planner, an important question to…
Repeated plant monitoring is essential for tracking crop growth, and 3D reconstruction enables consistent comparison across monitoring sessions. However, rebuilding a 3D model from scratch in every session is costly and overlooks…
Essential for improving the accuracy and reliability of bowel cancer screening, three-dimensional (3D) surface reconstruction using capsule endoscopy (CE) images remains challenging due to CE hardware and software limitations. This report…