Related papers: EMIE-MAP: Large-Scale Road Surface Reconstruction …
Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former…
Leveraging 3D information within Multimodal Large Language Models (MLLMs) has recently shown significant advantages for indoor scene understanding. However, existing methods, including those using explicit ground-truth 3D positional…
How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…
We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation -- multi-implicit-submap. Different from existing neural RGB-D reconstruction methods lacking either…
3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction.…
Accurate detection of lane and road markings is a task of great importance for intelligent vehicles. In existing approaches, the detection accuracy often degrades with the increasing distance. This is due to the fact that distant lane and…
Implicit neural representations have demonstrated significant promise for 3D scene reconstruction. Recent works have extended their applications to autonomous implicit reconstruction through the Next Best View (NBV) based method. However,…
LIDAR sensors are usually used to provide autonomous vehicles with 3D representations of their environment. In ideal conditions, geometrical models could detect the road in LIDAR scans, at the cost of a manual tuning of numerical…
Collision detection is essential to virtually all robotics applications. However, traditional geometric collision detection methods generally require pre-existing workspace geometry representations; thus, they are unable to infer the…
Whereas dedicated scene representations are required for each different task in conventional robotic systems, this paper demonstrates that a unified representation can be used directly for multiple key tasks. We propose the Log-Gaussian…
Robotic applications require a comprehensive understanding of the scene. In recent years, neural fields-based approaches that parameterize the entire environment have become popular. These approaches are promising due to their continuous…
Previous multi-view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrinsics and the camera-to-object distance. Consequently, when…
Despite the promising results of multi-view reconstruction, the recent neural rendering-based methods, such as implicit surface rendering (IDR) and volume rendering (NeuS), not only incur a heavy computational burden on training but also…
Recent works on implicit neural representations have made significant strides. Learning implicit neural surfaces using volume rendering has gained popularity in multi-view reconstruction without 3D supervision. However, accurately…
Inferring road graphs from satellite imagery is a challenging computer vision task. Prior solutions fall into two categories: (1) pixel-wise segmentation-based approaches, which predict whether each pixel is on a road, and (2) graph-based…
Learning neural implicit surfaces from volume rendering has become popular for multi-view reconstruction. Neural surface reconstruction approaches can recover complex 3D geometry that are difficult for classical Multi-view Stereo (MVS)…
We present Uni-Fusion, a universal continuous mapping framework for surfaces, surface properties (color, infrared, etc.) and more (latent features in CLIP embedding space, etc.). We propose the first universal implicit encoding model that…
Neural implicit representations have had a significant impact on simultaneous localization and mapping (SLAM) by enabling robots to build continuous, differentiable, and high-fidelity 3D maps from sensor data. However, as the scale and…
Scene understanding is an important capability for robots acting in unstructured environments. While most SLAM approaches provide a geometrical representation of the scene, a semantic map is necessary for more complex interactions with the…
In this work, we present a new method for 3D face reconstruction from sparse-view RGB images. Unlike previous methods which are built upon 3D morphable models (3DMMs) with limited details, we leverage an implicit representation to encode…