Related papers: DL3DV-10K: A Large-Scale Scene Dataset for Deep Le…
Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…
High-resolution datasets are essential for advancing super-resolution (SR) and text-to-image (T2I) diffusion research. However, current publicly available datasets lack both the native 4K resolution and the extensive scale necessary for…
Recent novel view synthesis (NVS) techniques, including Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have greatly advanced 3D scene reconstruction with high-quality rendering and realistic detail recovery. Effectively…
The Deep Learning Visual Space Simulation System (DLVS3) introduces a novel synthetic dataset generator and a simulation pipeline specifically designed for training and testing satellite pose estimation solutions. This work introduces the…
Depth estimation (DE) provides spatial information about a scene and enables tasks such as 3D reconstruction, object detection, and scene understanding. Recently, there has been an increasing interest in using deep learning (DL)-based…
To facilitate depth-based 3D action recognition, 3D dynamic voxel (3DV) is proposed as a novel 3D motion representation. With 3D space voxelization, the key idea of 3DV is to encode 3D motion information within depth video into a regular…
The prevalence of violence in daily life poses significant threats to individuals' physical and mental well-being. Using surveillance cameras in public spaces has proven effective in proactively deterring and preventing such incidents.…
Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only…
Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera…
With the recent rise of Large Language Models (LLMs), Vision-Language Models (VLMs), and other general foundation models, there is growing potential for multimodal, multi-task embodied agents that can operate in diverse environments given…
We propose DistillNeRF, a self-supervised learning framework addressing the challenge of understanding 3D environments from limited 2D observations in outdoor autonomous driving scenes. Our method is a generalizable feedforward model that…
3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as immersive media, robotics, autonomous driving, and embodied AI. Early methods based on…
We have built a custom mobile multi-camera large-space dense light field capture system, which provides a series of high-quality and sufficiently dense light field images for various scenarios. Our aim is to contribute to the development of…
Novel view synthesis refers to the problem of synthesizing novel viewpoints of a scene given the images from a few viewpoints. This is a fundamental problem in computer vision and graphics, and enables a vast variety of applications such as…
Neural Radiance Field (NeRF) has revolutionized novel-view rendering tasks and achieved impressive results. However, the inefficient sampling and per-scene optimization hinder its wide applications. Though some generalizable NeRFs have been…
Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy. The current best solution is to subsequently employ best models of…
The application of methods based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3D GS) have steadily gained popularity in the field of 3D object segmentation in static scenes. These approaches demonstrate efficacy in a range of…
In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis. To this end, we propose DeepVoxels, a learned representation that encodes the…
We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene…
Domain scientists often face I/O and storage challenges when keeping raw data from large-scale simulations. Saving visualization images, albeit practical, is limited to preselected viewpoints, transfer functions, and simulation parameters.…