A Survey on Monocular Re-Localization: From the Perspective of Scene Map Representation

Monocular Re-Localization (MRL) is a critical component in numerous autonomous applications, which estimates 6 degree-of-freedom poses with regards to the scene map based on a single monocular image. In recent decades, significant progress has been made in the development of MRL techniques. Numerous landmark algorithms have accomplished extraordinary success in terms of localization accuracy and robustness against visual interference. In MRL research, scene maps are represented in various forms, and they determine how MRL methods work and even how MRL methods perform. However, to the best of our knowledge, existing surveys do not provide systematic reviews of MRL from the respective of map. This survey fills the gap by comprehensively reviewing MRL methods employing monocular cameras as main sensors, promoting further research. 1) We commence by delving into the problem definition of MRL and exploring current challenges, while also comparing ours with with previous published surveys. 2) MRL methods are then categorized into five classes according to the representation forms of utilized map, i.e., geo-tagged frames, visual landmarks, point clouds, and vectorized semantic map, and we review the milestone MRL works of each category. 3) To quantitatively and fairly compare MRL methods with various map, we also review some public datasets and provide the performances of some typical MRL methods. The strengths and weakness of different types of MRL methods are analyzed. 4) We finally introduce some topics of interest in this field and give personal opinions. This survey can serve as a valuable referenced materials for newcomers and researchers interested in MRL, and a continuously updated summary of this survey, including reviewed papers and datasets, is publicly available to the community at: https://github.com/jinyummiao/map-in-mono-reloc.

FuseSR: Super Resolution for Real-time Rendering through Efficient Multi-resolution Fusion

The workload of real-time rendering is steeply increasing as the demand for high resolution, high refresh rates, and high realism rises, overwhelming most graphics cards. To mitigate this problem, one of the most popular solutions is to render images at a low resolution to reduce rendering overhead, and then manage to accurately upsample the low-resolution rendered image to the target resolution, a.k.a. super-resolution techniques. Most existing methods focus on exploiting information from low-resolution inputs, such as historical frames. The absence of high frequency details in those LR inputs makes them hard to recover fine details in their high-resolution predictions. In this paper, we propose an efficient and effective super-resolution method that predicts high-quality upsampled reconstructions utilizing low-cost high-resolution auxiliary G-Buffers as additional input. With LR images and HR G-buffers as input, the network requires to align and fuse features at multi resolution levels. We introduce an efficient and effective H-Net architecture to solve this problem and significantly reduce rendering overhead without noticeable quality deterioration. Experiments show that our method is able to produce temporally consistent reconstructions in $4 \times 4$ and even challenging $8 \times 8$ upsampling cases at 4K resolution with real-time performance, with substantially improved quality and significant performance boost compared to existing works.

Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields

With the popularity of implicit neural representations, or neural radiance fields (NeRF), there is a pressing need for editing methods to interact with the implicit 3D models for tasks like post-processing reconstructed scenes and 3D content creation. While previous works have explored NeRF editing from various perspectives, they are restricted in editing flexibility, quality, and speed, failing to offer direct editing response and instant preview. The key challenge is to conceive a locally editable neural representation that can directly reflect the editing instructions and update instantly. To bridge the gap, we propose a new interactive editing method and system for implicit representations, called Seal-3D, which allows users to edit NeRF models in a pixel-level and free manner with a wide range of NeRF-like backbone and preview the editing effects instantly. To achieve the effects, the challenges are addressed by our proposed proxy function mapping the editing instructions to the original space of NeRF models and a teacher-student training strategy with local pretraining and global finetuning. A NeRF editing system is built to showcase various editing types. Our system can achieve compelling editing effects with an interactive speed of about 1 second.

Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing

Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-to-end, learning-based inverse rendering framework incorporating differentiable Monte Carlo raytracing with importance sampling. The framework takes a single image as input to jointly recover the underlying geometry, spatially-varying lighting, and photorealistic materials. Specifically, we introduce a physically-based differentiable rendering layer with screen-space ray tracing, resulting in more realistic specular reflections that match the input photo. In addition, we create a large-scale, photorealistic indoor scene dataset with significantly richer details like complex furniture and dedicated decorations. Further, we design a novel out-of-view lighting network with uncertainty-aware refinement leveraging hypernetwork-based neural radiance fields to predict lighting outside the view of the input photo. Through extensive evaluations on common benchmark datasets, we demonstrate superior inverse rendering quality of our method compared to state-of-the-art baselines, enabling various applications such as complex object insertion and material editing with high fidelity. Code and data will be made available at \url{https://jingsenzhu.github.io/invrend}.